trying to fix cython difficulties

previous commit

LICENSE

@@ -0,0 +1,518 @@
+
+  CeCILL FREE SOFTWARE LICENSE AGREEMENT
+
+Version 2.1 dated 2013-06-21
+
+
+    Notice
+
+This Agreement is a Free Software license agreement that is the result
+of discussions between its authors in order to ensure compliance with
+the two main principles guiding its drafting:
+
+  * firstly, compliance with the principles governing the distribution
+    of Free Software: access to source code, broad rights granted to users,
+  * secondly, the election of a governing law, French law, with which it
+    is conformant, both as regards the law of torts and intellectual
+    property law, and the protection that it offers to both authors and
+    holders of the economic rights over software.
+
+The authors of the CeCILL (for Ce[a] C[nrs] I[nria] L[ogiciel] L[ibre]) 
+license are: 
+
+Commissariat à l'énergie atomique et aux énergies alternatives - CEA, a
+public scientific, technical and industrial research establishment,
+having its principal place of business at 25 rue Leblanc, immeuble Le
+Ponant D, 75015 Paris, France.
+
+Centre National de la Recherche Scientifique - CNRS, a public scientific
+and technological establishment, having its principal place of business
+at 3 rue Michel-Ange, 75794 Paris cedex 16, France.
+
+Institut National de Recherche en Informatique et en Automatique -
+Inria, a public scientific and technological establishment, having its
+principal place of business at Domaine de Voluceau, Rocquencourt, BP
+105, 78153 Le Chesnay cedex, France.
+
+
+    Preamble
+
+The purpose of this Free Software license agreement is to grant users
+the right to modify and redistribute the software governed by this
+license within the framework of an open source distribution model.
+
+The exercising of this right is conditional upon certain obligations for
+users so as to preserve this status for all subsequent redistributions.
+
+In consideration of access to the source code and the rights to copy,
+modify and redistribute granted by the license, users are provided only
+with a limited warranty and the software's author, the holder of the
+economic rights, and the successive licensors only have limited liability.
+
+In this respect, the risks associated with loading, using, modifying
+and/or developing or reproducing the software by the user are brought to
+the user's attention, given its Free Software status, which may make it
+complicated to use, with the result that its use is reserved for
+developers and experienced professionals having in-depth computer
+knowledge. Users are therefore encouraged to load and test the
+suitability of the software as regards their requirements in conditions
+enabling the security of their systems and/or data to be ensured and,
+more generally, to use and operate it in the same conditions of
+security. This Agreement may be freely reproduced and published,
+provided it is not altered, and that no provisions are either added or
+removed herefrom.
+
+This Agreement may apply to any or all software for which the holder of
+the economic rights decides to submit the use thereof to its provisions.
+
+Frequently asked questions can be found on the official website of the
+CeCILL licenses family (http://www.cecill.info/index.en.html) for any 
+necessary clarification.
+
+
+    Article 1 - DEFINITIONS
+
+For the purpose of this Agreement, when the following expressions
+commence with a capital letter, they shall have the following meaning:
+
+Agreement: means this license agreement, and its possible subsequent
+versions and annexes.
+
+Software: means the software in its Object Code and/or Source Code form
+and, where applicable, its documentation, "as is" when the Licensee
+accepts the Agreement.
+
+Initial Software: means the Software in its Source Code and possibly its
+Object Code form and, where applicable, its documentation, "as is" when
+it is first distributed under the terms and conditions of the Agreement.
+
+Modified Software: means the Software modified by at least one
+Contribution.
+
+Source Code: means all the Software's instructions and program lines to
+which access is required so as to modify the Software.
+
+Object Code: means the binary files originating from the compilation of
+the Source Code.
+
+Holder: means the holder(s) of the economic rights over the Initial
+Software.
+
+Licensee: means the Software user(s) having accepted the Agreement.
+
+Contributor: means a Licensee having made at least one Contribution.
+
+Licensor: means the Holder, or any other individual or legal entity, who
+distributes the Software under the Agreement.
+
+Contribution: means any or all modifications, corrections, translations,
+adaptations and/or new functions integrated into the Software by any or
+all Contributors, as well as any or all Internal Modules.
+
+Module: means a set of sources files including their documentation that
+enables supplementary functions or services in addition to those offered
+by the Software.
+
+External Module: means any or all Modules, not derived from the
+Software, so that this Module and the Software run in separate address
+spaces, with one calling the other when they are run.
+
+Internal Module: means any or all Module, connected to the Software so
+that they both execute in the same address space.
+
+GNU GPL: means the GNU General Public License version 2 or any
+subsequent version, as published by the Free Software Foundation Inc.
+
+GNU Affero GPL: means the GNU Affero General Public License version 3 or
+any subsequent version, as published by the Free Software Foundation Inc.
+
+EUPL: means the European Union Public License version 1.1 or any
+subsequent version, as published by the European Commission.
+
+Parties: mean both the Licensee and the Licensor.
+
+These expressions may be used both in singular and plural form.
+
+
+    Article 2 - PURPOSE
+
+The purpose of the Agreement is the grant by the Licensor to the
+Licensee of a non-exclusive, transferable and worldwide license for the
+Software as set forth in Article 5 <#scope> hereinafter for the whole
+term of the protection granted by the rights over said Software.
+
+
+    Article 3 - ACCEPTANCE
+
+3.1 The Licensee shall be deemed as having accepted the terms and
+conditions of this Agreement upon the occurrence of the first of the
+following events:
+
+  * (i) loading the Software by any or all means, notably, by
+    downloading from a remote server, or by loading from a physical medium;
+  * (ii) the first time the Licensee exercises any of the rights granted
+    hereunder.
+
+3.2 One copy of the Agreement, containing a notice relating to the
+characteristics of the Software, to the limited warranty, and to the
+fact that its use is restricted to experienced users has been provided
+to the Licensee prior to its acceptance as set forth in Article 3.1
+<#accepting> hereinabove, and the Licensee hereby acknowledges that it
+has read and understood it.
+
+
+    Article 4 - EFFECTIVE DATE AND TERM
+
+
+      4.1 EFFECTIVE DATE
+
+The Agreement shall become effective on the date when it is accepted by
+the Licensee as set forth in Article 3.1 <#accepting>.
+
+
+      4.2 TERM
+
+The Agreement shall remain in force for the entire legal term of
+protection of the economic rights over the Software.
+
+
+    Article 5 - SCOPE OF RIGHTS GRANTED
+
+The Licensor hereby grants to the Licensee, who accepts, the following
+rights over the Software for any or all use, and for the term of the
+Agreement, on the basis of the terms and conditions set forth hereinafter.
+
+Besides, if the Licensor owns or comes to own one or more patents
+protecting all or part of the functions of the Software or of its
+components, the Licensor undertakes not to enforce the rights granted by
+these patents against successive Licensees using, exploiting or
+modifying the Software. If these patents are transferred, the Licensor
+undertakes to have the transferees subscribe to the obligations set
+forth in this paragraph.
+
+
+      5.1 RIGHT OF USE
+
+The Licensee is authorized to use the Software, without any limitation
+as to its fields of application, with it being hereinafter specified
+that this comprises:
+
+ 1. permanent or temporary reproduction of all or part of the Software
+    by any or all means and in any or all form.
+
+ 2. loading, displaying, running, or storing the Software on any or all
+    medium.
+
+ 3. entitlement to observe, study or test its operation so as to
+    determine the ideas and principles behind any or all constituent
+    elements of said Software. This shall apply when the Licensee
+    carries out any or all loading, displaying, running, transmission or
+    storage operation as regards the Software, that it is entitled to
+    carry out hereunder.
+
+
+      5.2 ENTITLEMENT TO MAKE CONTRIBUTIONS
+
+The right to make Contributions includes the right to translate, adapt,
+arrange, or make any or all modifications to the Software, and the right
+to reproduce the resulting software.
+
+The Licensee is authorized to make any or all Contributions to the
+Software provided that it includes an explicit notice that it is the
+author of said Contribution and indicates the date of the creation thereof.
+
+
+      5.3 RIGHT OF DISTRIBUTION
+
+In particular, the right of distribution includes the right to publish,
+transmit and communicate the Software to the general public on any or
+all medium, and by any or all means, and the right to market, either in
+consideration of a fee, or free of charge, one or more copies of the
+Software by any means.
+
+The Licensee is further authorized to distribute copies of the modified
+or unmodified Software to third parties according to the terms and
+conditions set forth hereinafter.
+
+
+        5.3.1 DISTRIBUTION OF SOFTWARE WITHOUT MODIFICATION
+
+The Licensee is authorized to distribute true copies of the Software in
+Source Code or Object Code form, provided that said distribution
+complies with all the provisions of the Agreement and is accompanied by:
+
+ 1. a copy of the Agreement,
+
+ 2. a notice relating to the limitation of both the Licensor's warranty
+    and liability as set forth in Articles 8 and 9,
+
+and that, in the event that only the Object Code of the Software is
+redistributed, the Licensee allows effective access to the full Source
+Code of the Software for a period of at least three years from the
+distribution of the Software, it being understood that the additional
+acquisition cost of the Source Code shall not exceed the cost of the
+data transfer.
+
+
+        5.3.2 DISTRIBUTION OF MODIFIED SOFTWARE
+
+When the Licensee makes a Contribution to the Software, the terms and
+conditions for the distribution of the resulting Modified Software
+become subject to all the provisions of this Agreement.
+
+The Licensee is authorized to distribute the Modified Software, in
+source code or object code form, provided that said distribution
+complies with all the provisions of the Agreement and is accompanied by:
+
+ 1. a copy of the Agreement,
+
+ 2. a notice relating to the limitation of both the Licensor's warranty
+    and liability as set forth in Articles 8 and 9,
+
+and, in the event that only the object code of the Modified Software is
+redistributed,
+
+ 3. a note stating the conditions of effective access to the full source
+    code of the Modified Software for a period of at least three years
+    from the distribution of the Modified Software, it being understood
+    that the additional acquisition cost of the source code shall not
+    exceed the cost of the data transfer.
+
+
+        5.3.3 DISTRIBUTION OF EXTERNAL MODULES
+
+When the Licensee has developed an External Module, the terms and
+conditions of this Agreement do not apply to said External Module, that
+may be distributed under a separate license agreement.
+
+
+        5.3.4 COMPATIBILITY WITH OTHER LICENSES
+
+The Licensee can include a code that is subject to the provisions of one
+of the versions of the GNU GPL, GNU Affero GPL and/or EUPL in the
+Modified or unmodified Software, and distribute that entire code under
+the terms of the same version of the GNU GPL, GNU Affero GPL and/or EUPL.
+
+The Licensee can include the Modified or unmodified Software in a code
+that is subject to the provisions of one of the versions of the GNU GPL,
+GNU Affero GPL and/or EUPL and distribute that entire code under the
+terms of the same version of the GNU GPL, GNU Affero GPL and/or EUPL.
+
+
+    Article 6 - INTELLECTUAL PROPERTY
+
+
+      6.1 OVER THE INITIAL SOFTWARE
+
+The Holder owns the economic rights over the Initial Software. Any or
+all use of the Initial Software is subject to compliance with the terms
+and conditions under which the Holder has elected to distribute its work
+and no one shall be entitled to modify the terms and conditions for the
+distribution of said Initial Software.
+
+The Holder undertakes that the Initial Software will remain ruled at
+least by this Agreement, for the duration set forth in Article 4.2 <#term>.
+
+
+      6.2 OVER THE CONTRIBUTIONS
+
+The Licensee who develops a Contribution is the owner of the
+intellectual property rights over this Contribution as defined by
+applicable law.
+
+
+      6.3 OVER THE EXTERNAL MODULES
+
+The Licensee who develops an External Module is the owner of the
+intellectual property rights over this External Module as defined by
+applicable law and is free to choose the type of agreement that shall
+govern its distribution.
+
+
+      6.4 JOINT PROVISIONS
+
+The Licensee expressly undertakes:
+
+ 1. not to remove, or modify, in any manner, the intellectual property
+    notices attached to the Software;
+
+ 2. to reproduce said notices, in an identical manner, in the copies of
+    the Software modified or not.
+
+The Licensee undertakes not to directly or indirectly infringe the
+intellectual property rights on the Software of the Holder and/or
+Contributors, and to take, where applicable, vis-à-vis its staff, any
+and all measures required to ensure respect of said intellectual
+property rights of the Holder and/or Contributors.
+
+
+    Article 7 - RELATED SERVICES
+
+7.1 Under no circumstances shall the Agreement oblige the Licensor to
+provide technical assistance or maintenance services for the Software.
+
+However, the Licensor is entitled to offer this type of services. The
+terms and conditions of such technical assistance, and/or such
+maintenance, shall be set forth in a separate instrument. Only the
+Licensor offering said maintenance and/or technical assistance services
+shall incur liability therefor.
+
+7.2 Similarly, any Licensor is entitled to offer to its licensees, under
+its sole responsibility, a warranty, that shall only be binding upon
+itself, for the redistribution of the Software and/or the Modified
+Software, under terms and conditions that it is free to decide. Said
+warranty, and the financial terms and conditions of its application,
+shall be subject of a separate instrument executed between the Licensor
+and the Licensee.
+
+
+    Article 8 - LIABILITY
+
+8.1 Subject to the provisions of Article 8.2, the Licensee shall be
+entitled to claim compensation for any direct loss it may have suffered
+from the Software as a result of a fault on the part of the relevant
+Licensor, subject to providing evidence thereof.
+
+8.2 The Licensor's liability is limited to the commitments made under
+this Agreement and shall not be incurred as a result of in particular:
+(i) loss due the Licensee's total or partial failure to fulfill its
+obligations, (ii) direct or consequential loss that is suffered by the
+Licensee due to the use or performance of the Software, and (iii) more
+generally, any consequential loss. In particular the Parties expressly
+agree that any or all pecuniary or business loss (i.e. loss of data,
+loss of profits, operating loss, loss of customers or orders,
+opportunity cost, any disturbance to business activities) or any or all
+legal proceedings instituted against the Licensee by a third party,
+shall constitute consequential loss and shall not provide entitlement to
+any or all compensation from the Licensor.
+
+
+    Article 9 - WARRANTY
+
+9.1 The Licensee acknowledges that the scientific and technical
+state-of-the-art when the Software was distributed did not enable all
+possible uses to be tested and verified, nor for the presence of
+possible defects to be detected. In this respect, the Licensee's
+attention has been drawn to the risks associated with loading, using,
+modifying and/or developing and reproducing the Software which are
+reserved for experienced users.
+
+The Licensee shall be responsible for verifying, by any or all means,
+the suitability of the product for its requirements, its good working
+order, and for ensuring that it shall not cause damage to either persons
+or properties.
+
+9.2 The Licensor hereby represents, in good faith, that it is entitled
+to grant all the rights over the Software (including in particular the
+rights set forth in Article 5 <#scope>).
+
+9.3 The Licensee acknowledges that the Software is supplied "as is" by
+the Licensor without any other express or tacit warranty, other than
+that provided for in Article 9.2 <#good-faith> and, in particular,
+without any warranty as to its commercial value, its secured, safe,
+innovative or relevant nature.
+
+Specifically, the Licensor does not warrant that the Software is free
+from any error, that it will operate without interruption, that it will
+be compatible with the Licensee's own equipment and software
+configuration, nor that it will meet the Licensee's requirements.
+
+9.4 The Licensor does not either expressly or tacitly warrant that the
+Software does not infringe any third party intellectual property right
+relating to a patent, software or any other property right. Therefore,
+the Licensor disclaims any and all liability towards the Licensee
+arising out of any or all proceedings for infringement that may be
+instituted in respect of the use, modification and redistribution of the
+Software. Nevertheless, should such proceedings be instituted against
+the Licensee, the Licensor shall provide it with technical and legal
+expertise for its defense. Such technical and legal expertise shall be
+decided on a case-by-case basis between the relevant Licensor and the
+Licensee pursuant to a memorandum of understanding. The Licensor
+disclaims any and all liability as regards the Licensee's use of the
+name of the Software. No warranty is given as regards the existence of
+prior rights over the name of the Software or as regards the existence
+of a trademark.
+
+
+    Article 10 - TERMINATION
+
+10.1 In the event of a breach by the Licensee of its obligations
+hereunder, the Licensor may automatically terminate this Agreement
+thirty (30) days after notice has been sent to the Licensee and has
+remained ineffective.
+
+10.2 A Licensee whose Agreement is terminated shall no longer be
+authorized to use, modify or distribute the Software. However, any
+licenses that it may have granted prior to termination of the Agreement
+shall remain valid subject to their having been granted in compliance
+with the terms and conditions hereof.
+
+
+    Article 11 - MISCELLANEOUS
+
+
+      11.1 EXCUSABLE EVENTS
+
+Neither Party shall be liable for any or all delay, or failure to
+perform the Agreement, that may be attributable to an event of force
+majeure, an act of God or an outside cause, such as defective
+functioning or interruptions of the electricity or telecommunications
+networks, network paralysis following a virus attack, intervention by
+government authorities, natural disasters, water damage, earthquakes,
+fire, explosions, strikes and labor unrest, war, etc.
+
+11.2 Any failure by either Party, on one or more occasions, to invoke
+one or more of the provisions hereof, shall under no circumstances be
+interpreted as being a waiver by the interested Party of its right to
+invoke said provision(s) subsequently.
+
+11.3 The Agreement cancels and replaces any or all previous agreements,
+whether written or oral, between the Parties and having the same
+purpose, and constitutes the entirety of the agreement between said
+Parties concerning said purpose. No supplement or modification to the
+terms and conditions hereof shall be effective as between the Parties
+unless it is made in writing and signed by their duly authorized
+representatives.
+
+11.4 In the event that one or more of the provisions hereof were to
+conflict with a current or future applicable act or legislative text,
+said act or legislative text shall prevail, and the Parties shall make
+the necessary amendments so as to comply with said act or legislative
+text. All other provisions shall remain effective. Similarly, invalidity
+of a provision of the Agreement, for any reason whatsoever, shall not
+cause the Agreement as a whole to be invalid.
+
+
+      11.5 LANGUAGE
+
+The Agreement is drafted in both French and English and both versions
+are deemed authentic.
+
+
+    Article 12 - NEW VERSIONS OF THE AGREEMENT
+
+12.1 Any person is authorized to duplicate and distribute copies of this
+Agreement.
+
+12.2 So as to ensure coherence, the wording of this Agreement is
+protected and may only be modified by the authors of the License, who
+reserve the right to periodically publish updates or new versions of the
+Agreement, each with a separate number. These subsequent versions may
+address new issues encountered by Free Software.
+
+12.3 Any Software distributed under a given version of the Agreement may
+only be subsequently distributed under the same version of the Agreement
+or a subsequent version, subject to the provisions of Article 5.3.4
+<#compatibility>.
+
+
+    Article 13 - GOVERNING LAW AND JURISDICTION
+
+13.1 The Agreement is governed by French law. The Parties agree to
+endeavor to seek an amicable solution to any disagreements or disputes
+that may arise during the performance of the Agreement.
+
+13.2 Failing an amicable solution within two (2) months as from their
+occurrence, and unless emergency proceedings are necessary, the
+disagreements or disputes shall be referred to the Paris Courts having
+jurisdiction, by the more diligent Party.

README.md

@@ -0,0 +1,40 @@
+The `OBITools3`: A package for the management of analyses and data in DNA metabarcoding   
+---------------------------------------------
+
+
+
+DNA metabarcoding offers new perspectives for biodiversity research [1]. This approach of ecosystem studies relies heavily on the use of Next-Generation Sequencing (NGS), and consequently requires the ability to to treat large volumes of data. The `OBITools` package  satisfies this requirement thanks to a set of programs specifically designed for analyzing NGS data in a DNA metabarcoding context [2] - <http://metabarcoding.org/obitools>. Their capacity to filter and edit sequences while taking into account taxonomic annotation helps to setup tailored-made analysis pipelines for a broad range of DNA metabarcoding applications, including biodiversity surveys or diet analyses.   
+
+
+
+**The `OBITools3`.** This new version of the `OBITools` looks to significantly improve the storage efficiency and the data processing speed. To this end, the `OBITools3` rely on an ad hoc database system, inside which all the data that a DNA metabarcoding experiment must consider is stored: the sequences, the metadata (describing for instance the samples), the database containing the reference sequences used for the taxonomic annotation, as well as the taxonomic databases. Besides the gain in efficiency, this new structure allows an easier access to all the data associated with an experiment.   
+
+
+
+**Column-oriented storage.** An analysis pipeline corresponds to a succession of commands, each computing one step of the analysis, and where the result of the command *n* is used by the command *n+1*. DNA metabarcoding data can easily be represented in the form of tables, and each command can be regarded as an operation transforming one or several 'input' tables into one or several 'output' tables, which can be used by the next command. Many of the basic operations in a pipeline copy without modification an important part of the input tables to the result tables, and use for their calculations only a small part of the input data. In the original `OBITools`, those tables are kept in the form of annotated sequence files in the FASTA or FASTQ format. This has two consequences: i) keeping the transitional results of the analysis pipeline means using disk space for an important volume of redundant data, ii) The coding and decoding of informations that are not actually used represent an important part of the treatment process. The new database system used by the `OBITools3` (called DMS for Data Management System) relies on column-oriented storage. The columns are immutable and can be assembled in views representing the data tables. This way, the data not modified by a command in an input table can easily be associated to the result table without duplicating any information ; and the data not used at all by a command can be associated with the result table without being read. This strategy results in a gain in disk space efficiency by limiting data redundancy, as well as a gain in execution time by limiting data reading, writing and conversion operations. Finally, as a mean to optimize data access, each column is stored in a binary file directly mapped in memory for reading and writing operations.   
+
+
+
+**Storage optimization.** DNA metabarcoding data is intrinsically very redundant. For example, the same sequence corresponding to a species will be present several thousand times across all samples. In order to limit the disk space used and make comparison operations more efficient, data in the form of character strings is stored in columns using a complex indexing structure, efficient on millions of values, coupling hash functions, Bloom filters and AVL trees. Finally, DNA sequences are compressed by encoding each nucleotide on two or four bits depending on whether the sequences contain only the four nucleotides (A, C, G, T) or use the IUPAC codes.   
+
+
+
+**Saving the data processing history.** The totality of the informations used by the `OBITools3` is stored in immutable data structures in the DMS. If a command has to modify a column used as input to produce its result, a new version of that column is created, leaving the initial version intact. This storage system enables to keep, at minimal cost, the totality of the transitional results produced by the pipeline. The storage of metadata describing all the operations that have produced a view (a result table) in the DMS makes possible the creation of an oriented hypergraph, where each node corresponds to a view and each arrow to an operation. By retracing the dependency relationships in this hypergraph, it is possible to rebuild *a posteriori* the entirety of the process that has produced a result table.   
+
+
+
+**Tools.** The `OBITools3` offer the same tools as the original `OBITools`. Eventually, new versions of `ecoPrimers` (PCR primer design) [3], `ecoPCR` (*in silico* PCR) [4], as well as `Sumatra` (sequence alignment) and `Sumaclust` (sequence alignment and clustering) [5] will be added, taking advantage of the database structure developed for the `OBITools3`.    
+
+
+
+**Implementation and disponibility.** The lower layers managing the DMS as well as all the compute-intensive functions are coded in `C99` for efficiency reasons. A `Cython` (<http://www.cython.org>) object layer allows for a simple but efficient implementation of the `OBITools3` commands in `Python 3.5`. The `OBITools3` are still in development, and the first functional versions are expected for autumn 2016.    
+
+
+
+**References.**
+
+1. Taberlet P, Coissac E, Hajibabaei M, Rieseberg LH: Environmental DNA. Mol Ecol 2012:1789–1793.
+2. Boyer F, Mercier C, Bonin A, Le Bras Y, Taberlet P, Coissac E: OBITools: a Unix-inspired software package for DNA metabarcoding. Mol Ecol Resour 2015:n/a–n/a.
+3. Riaz T, Shehzad W, Viari A, Pompanon F, Taberlet P, Coissac E: ecoPrimers: inference of new DNA barcode markers from whole genome sequence analysis. Nucleic Acids Res 2011, 39:e145.
+4. Ficetola GF, Coissac E, Zundel S, Riaz T, Shehzad W, Bessière J, Taberlet P, Pompanon F: An in silico approach for the evaluation of DNA barcodes. BMC Genomics 2010, 11:434.
+5. Mercier C, Boyer F, Bonin A, Coissac E (2013) SUMATRA and SUMACLUST: fast and exact comparison and clustering of sequences. Available: <http://metabarcoding.org/sumatra> and <http://metabarcoding.org/sumaclust>

distutils.ext/obidistutils/command/build_exe.py

@@ -6,12 +6,28 @@ Created on 20 oct. 2012
 
 import os
 
+from distutils import sysconfig
 from distutils.core import Command
-from distutils.sysconfig import customize_compiler
+from distutils.sysconfig import customize_compiler as customize_compiler_ori
 from distutils.errors import DistutilsSetupError
 from distutils import log
 from distutils.ccompiler import show_compilers
 
+def customize_compiler(compiler):
+    customize_compiler_ori(compiler)
+    compilername = compiler.compiler[0]
+    if ("gcc" in compilername or "g++" in compilername):
+        cc_cmd = ' '.join(compiler.compiler + ['-fopenmp'])
+        ccshared= ' '.join(x for x in sysconfig.get_config_vars("ccshared") if x is not None)
+            
+        compiler.set_executables(
+            compiler=cc_cmd,
+            compiler_so=cc_cmd + ' ' + ccshared
+            )
+            
+    
+    
+
 class build_exe(Command):
     
     description = "build an executable -- Abstract command "
@@ -80,6 +96,7 @@ class build_exe(Command):
             else:
                 self.extra_compile_args.append('-m%s' % self.sse)
 
+
         # XXX same as for build_ext -- what about 'self.define' and
         # 'self.undef' ?
 

distutils.ext/obidistutils/command/build_ext.py

@@ -7,16 +7,32 @@ Created on 13 fevr. 2014
 from distutils import log
 import os
 
-from Cython.Distutils import build_ext  as ori_build_ext  # @UnresolvedImport
-
-from Cython.Compiler import Options as cython_options  # @UnresolvedImport
-
+from distutils import sysconfig
 from distutils.errors import DistutilsSetupError
 
+def _customize_compiler(compiler):
+    compilername = compiler.compiler[0]
+    if ("gcc" in compilername or "g++" in compilername):
+        cc_cmd  = ' '.join(compiler.compiler + ['-fopenmp'])
+        ccshared= ' '.join(x for x in sysconfig.get_config_vars("ccshared") if x is not None)
+            
+        compiler.set_executables(
+            compiler=cc_cmd,
+            compiler_so=cc_cmd + ' ' + ccshared
+            )
+
+
+try:
+    from Cython.Distutils import build_ext  as ori_build_ext  # @UnresolvedImport
+    from Cython.Compiler import Options as cython_options  # @UnresolvedImport
     class build_ext(ori_build_ext):
     
         
         def modifyDocScripts(self):
+            try:
+                os.mkdir("doc/sphinx")
+            except:
+                pass
             build_dir_file=open("doc/sphinx/build_dir.txt","w")
             print(self.build_lib,file=build_dir_file)
             build_dir_file.close()
@@ -28,7 +44,8 @@ class build_ext(ori_build_ext):
     
         
         def finalize_options(self):
-        ori_build_ext.finalize_options(self)  # @UndefinedVariable
+            super(build_ext, self).finalize_options()
+            
     
             self.set_undefined_options('littlebigman',
                                        ('littlebigman',  'littlebigman'))
@@ -80,11 +97,23 @@ class build_ext(ori_build_ext):
                 
             self.check_extensions_list(self.extensions)
             
+            print("pouic")
+            print(ext.sources)
+            print("pouac")
+            
             for ext in self.extensions:
                 log.info("%s :-> %s",ext.name,ext.sources)
                 ext.sources = self.cython_sources(ext.sources, ext)
                 self.build_extension(ext)
     
+        def build_extensions(self):  # TODO what?? double? is it supposed to be build_extension?
+            if hasattr(self, 'compiler'):
+                _customize_compiler(self.compiler)
+            if hasattr(self, 'shlib_compiler'):
+                _customize_compiler(self.shlib_compiler)
+            
+            ori_build_ext.build_extensions(self)
+
             
         def run(self):
             self.modifyDocScripts()
@@ -104,9 +133,10 @@ class build_ext(ori_build_ext):
         
         sub_commands = [('build_files',has_files),
                         ('build_cexe', has_executables)
-                    ] + \
-                   ori_build_ext.sub_commands
-
+                        ] + ori_build_ext.sub_commands 
+
+except ImportError:
+    from distutils.command import build_ext  # @UnusedImport
            
 
 

distutils.ext/obidistutils/core.py

@@ -9,13 +9,13 @@ import os.path
 import glob
 import sys
 
-# try:
-#     from setuptools.extension import Extension
-# except ImportError:
-#     from distutils.extension import Extension
-
+try:
+    from setuptools.extension import Extension
+except ImportError:
     from distutils.extension import Extension
 
+# from distutils.extension import Extension
+
 from obidistutils.serenity.checkpackage import  install_requirements,\
                                                 check_requirements, \
                                                 RequirementError
@@ -47,10 +47,16 @@ def findCython(root,base=None,pyrexs=None):
     for module in (path.basename(path.dirname(x)) 
                    for x in glob.glob(path.join(root,'*','__init__.py'))):
                                
-                
         for pyrex in glob.glob(path.join(root,module,'*.pyx')):
+            libabspath = os.path.abspath('obi_libdir')
+            obiabspath = os.path.abspath('.')
             pyrexs.append(Extension('.'.join(base+[module,path.splitext(path.basename(pyrex))[0]]),
-                                    [pyrex]
+                                    [pyrex],
+                                    library_dirs=[libabspath],
+                                    include_dirs=[libabspath],
+                                    libraries=["obi3"],
+                                    runtime_library_dirs=[libabspath],
+                                    extra_link_args=["-Wl,-rpath,"+libabspath, "-L"+libabspath]
                                     )
                           )
             try:
@@ -63,13 +69,15 @@ def findCython(root,base=None,pyrexs=None):
                 
                 log.info("Cython module : %s",cfiles)   
                 incdir = set(os.path.dirname(x) for x in cfiles if x[-2:]==".h")
-                cfiles = [x for x in cfiles if x[-2:]==".c"]                
-                pyrexs[-1].sources.extend(cfiles)
+                #cfiles = [x for x in cfiles if x[-2:]==".c"]                
+                #pyrexs[-1].sources.extend(cfiles)
                 pyrexs[-1].include_dirs.extend(incdir)
                 pyrexs[-1].extra_compile_args.extend(['-msse2',
                                                       '-Wno-unused-function',
                                                       '-Wmissing-braces',
-                                                      '-Wchar-subscripts'])
+                                                      '-Wchar-subscripts',
+                                                      '-fPIC'
+                                                      ])
                                 
             except IOError:
                 pass
@@ -135,7 +143,7 @@ def setup(**attrs):
     
     log.set_threshold(log.INFO)
     
-    minversion      = attrs.get("pythonmin",'3.4')
+    minversion      = attrs.get("pythonmin",'3.7')
     maxversion      = attrs.get('pythonmax',None)    
     fork            = attrs.get('fork',False)
     requirementfile = attrs.get('requirements','requirements.txt')
@@ -223,4 +231,4 @@ def setup(**attrs):
 
     from distutils.core import setup as ori_setup
     
-    ori_setup(**attrs)
+    return ori_setup(**attrs)

distutils.ext/obidistutils/dist.py

@@ -4,13 +4,13 @@ Created on 20 oct. 2012
 @author: coissac
 '''
 
-# try:
-#     from setuptools.dist import Distribution as ori_Distribution
-# except ImportError:
-#     from distutils.dist import Distribution as ori_Distribution
-
+try:
+    from setuptools.dist import Distribution as ori_Distribution
+except ImportError:
     from distutils.dist import Distribution as ori_Distribution
 
+# from distutils.dist import Distribution as ori_Distribution
+
 class Distribution(ori_Distribution):
     
     def __init__(self,attrs=None):

distutils.ext/obidistutils/serenity/__init__.py

@@ -81,9 +81,15 @@ def serenity_mode(package,version):
     argparser.add_argument('--serenity',
                            dest='serenity', 
                            action='store_true',
-                           default=False, 
+                           default=True, 
                            help='Switch the installer in serenity mode. Everythings are installed in a virtualenv')
 
+    argparser.add_argument('--no-serenity',
+                           dest='serenity', 
+                           action='store_false',
+                           default=True, 
+                           help='Switch the installer in the no serenity mode.')
+
     argparser.add_argument('--virtualenv',
                            dest='virtual', 
                            type=str,

distutils.ext/obidistutils/serenity/bootstrappip.py

@@ -0,0 +1,36 @@
+'''
+Created on 22 janv. 2016
+
+@author: coissac
+'''
+
+import sys
+from urllib import request
+import os.path
+
+from obidistutils.serenity.util import get_serenity_dir
+from obidistutils.serenity.rerun import rerun_with_anothe_python
+from obidistutils.serenity.checkpython import is_a_virtualenv_python
+
+getpipurl="https://bootstrap.pypa.io/get-pip.py"
+
+def bootstrap():
+
+    getpipfile=os.path.join(get_serenity_dir(),"get-pip.py")
+    
+    with request.urlopen(getpipurl) as getpip:
+        with open(getpipfile,"wb") as out:
+            for l in getpip:
+                out.write(l)
+                
+    python = sys.executable
+    
+    if is_a_virtualenv_python():
+        command= "%s %s" % (python,getpipfile)        
+    else:
+        command= "%s %s --user" % (python,getpipfile)
+    
+    os.system(command)
+    
+    rerun_with_anothe_python(python)
+    

distutils.ext/obidistutils/serenity/checkpackage.py

@@ -5,27 +5,35 @@ Created on 2 oct. 2014
 '''
 
 import re
-import os
 
-import pip                                              # @UnresolvedImport
-from pip.utils import get_installed_distributions       # @UnresolvedImport
 from distutils.version import StrictVersion             # @UnusedImport
 from distutils.errors import DistutilsError
 from distutils import log
 
+import os.path
+import sys
+import subprocess
+
+
 class RequirementError(Exception):
     pass
 
 def is_installed(requirement):
+    pipcommand = os.path.join(os.path.dirname(sys.executable),'pip')
+    pipjson    = subprocess.run([pipcommand,"list","--format=json"], 
+                                 capture_output=True).stdout
+    packages = eval(pipjson) 
+                                
     
     
     requirement_project,requirement_relation,requirement_version = parse_package_requirement(requirement)
     
-    package = [x for x in get_installed_distributions() if x.project_name==requirement_project]
+    package = [x for x in packages if x["name"]==requirement_project]
     
     if len(package)==1:
-        if requirement_version is not None and requirement_relation is not None:    
-            rep = (len(package)==1) and eval("StrictVersion('%s') %s StrictVersion('%s')" % (package[0].version,
+        if (     requirement_version is not None 
+             and requirement_relation is not None):    
+            rep = (len(package)==1) and eval("StrictVersion('%s') %s StrictVersion('%s')" % (package[0]["version"],
                                                                                            requirement_relation,
                                                                                            requirement_version)
                                              )
@@ -39,20 +47,23 @@ def is_installed(requirement):
             log.info("Look for package %s (%s%s) : ok version %s installed" % (requirement_project,
                                                                                requirement_relation,
                                                                                requirement_version,
-                                                                               package[0].version))
+                                                                               package[0]["version"]))
         else:
             log.info("Look for package %s : ok version %s installed" % (requirement_project,
-                                                                        package[0].version))
+                                                                        package[0]["version"]))
     else:
         if len(package)!=1:
+            if requirement_version is not None and requirement_relation is not None: 
                 log.info("Look for package %s (%s%s) : not installed" % (requirement_project,
                                                                          requirement_relation,
                                                                          requirement_version))
+            else:
+                log.info("Look for package %s : not installed" % requirement_project)                
         else:
             log.info("Look for package %s (%s%s) : failed only version %s installed" % (requirement_project,
                                                                                         requirement_relation,
                                                                                         requirement_version,
-                                                                                        package[0].version))
+                                                                                        package[0]["version"]))
         
     return rep
 
@@ -81,7 +92,7 @@ def install_requirements(requirementfile='requirements.txt'):
         ok = is_installed(x)
         if not ok:
             log.info("  Installing requirement : %s" % x)
-            pip_install_package(x)
+            pip_install_package(x,requirement=requirementfile)
             install_something=True
             if x[0:3]=='pip':
                 return True
@@ -134,8 +145,9 @@ def get_package_requirement(package,requirementfile='requirements.txt'):
         return None
         
         
-def pip_install_package(package,directory=None,upgrade=True):
+def pip_install_package(package,directory=None,requirement=None):
 
+    pipcommand = os.path.join(os.path.dirname(sys.executable),'pip')
     if directory is not None:
         log.info('    installing %s in directory %s' % (package,str(directory)))
         
@@ -145,8 +157,9 @@ def pip_install_package(package,directory=None,upgrade=True):
 
     args = ['install']
     
-    if upgrade:
-        args.append('--upgrade')
+    if requirement:
+        args.append('--requirement')
+        args.append(requirement)
     
     if 'https_proxy' in os.environ:
         args.append('--proxy=%s' % os.environ['https_proxy'])
@@ -156,5 +169,7 @@ def pip_install_package(package,directory=None,upgrade=True):
     
     args.append(package)
         
-    return pip.main(args)
+    pip = subprocess.run([pipcommand] + args)
+    
+    return pip
 

doc/conf.py

@@ -33,10 +33,10 @@ extensions = [
     'sphinx.ext.autodoc',
     'sphinx.ext.todo',
     'sphinx.ext.coverage',
-    'sphinx.ext.pngmath',
+    'sphinx.ext.imgmath',
     'sphinx.ext.ifconfig',
     'sphinx.ext.viewcode',
-#    'breathe',
+    'breathe',
 ]
 
 # Add any paths that contain templates here, relative to this directory.
@@ -295,4 +295,6 @@ texinfo_documents = [
 sys.path.append( "breathe/" )
 breathe_projects = { "OBITools3": "doxygen/xml/" }
 breathe_default_project = "OBITools3"
-
+#breathe_projects_source = {
+#     "auto" : ( "../src", ["obidms.h", "obiavl.h"] )
+#     }

doc/source/index.rst

@@ -11,7 +11,7 @@ OBITools3 documentation
 
    Programming guidelines <guidelines>
    Data structures <data>
-
+   Code documentation <code_doc/codedoc>
 
 Indices and tables
 ------------------

doc/source/types.rst

@@ -4,6 +4,7 @@ OBITypes
 
     
 .. image:: ./UML/OBITypes_UML.png
+
 :download:`html version of the OBITypes UML file <UML/OBITypes_UML.class.violet.html>`
 
 

doc/sphinx/build_dir.txt

@@ -1 +0,0 @@
-build/lib.macosx-10.6-intel-3.5

python/obi.py

@@ -0,0 +1,71 @@
+#!/usr/local/bin/python3.4
+'''
+obi -- shortdesc
+
+obi is a description
+
+It defines classes_and_methods
+
+@author:     user_name
+
+@copyright:  2014 organization_name. All rights reserved.
+
+@license:    license
+
+@contact:    user_email
+@deffield    updated: Updated
+'''
+
+
+default_config = { 'software'       : "The OBITools",
+                   'log'            : False,
+                   'loglevel'       : 'INFO',
+                   'progress'       : True,
+                   'inputURI'       : None,
+                   'outputURI'      : None,
+                   'defaultdms'     : None,
+                   'inputview'      : None,
+                   'outputview'     : None,
+                   'skip'           : 0,
+                   'only'           : None,
+                   'fileformat'     : None,
+                   'skiperror'      : True,
+                   'qualityformat'  : b'sanger',
+                   'offset'         : -1,
+                   'noquality'      : False,
+                   'seqtype'        : b'nuc',
+                   "header"         : False,
+                   "sep"            : None,
+                   "quote"          : [b"'",b'"'],
+                   "dec"            : b".",
+                   "nastring"       : b"NA",
+                   "stripwhite"     : True,
+                   "blanklineskip"  : True,
+                   "commentchar"    : b"#",
+                   "nocreatedms"    : False
+                  }
+
+root_config_name='obi'
+
+from obitools3.apps.config import getConfiguration     # @UnresolvedImport
+from obitools3.version import version
+
+__all__     = []
+__version__ = version
+__date__    = '2014-09-28'
+__updated__ = '2014-09-28'
+
+DEBUG = 1
+TESTRUN = 0
+PROFILE = 0
+
+
+if __name__ =="__main__":
+    
+    config = getConfiguration(root_config_name,
+                              default_config)    
+                
+    config[root_config_name]['module'].run(config)
+    
+    
+    

python/obitools3/apps/arguments.cfiles

@@ -0,0 +1,110 @@
+../../../src/obi_lcs.h
+../../../src/obi_lcs.c
+../../../src/obierrno.h
+../../../src/obierrno.c
+../../../src/upperband.h
+../../../src/upperband.c
+../../../src/sse_banded_LCS_alignment.h
+../../../src/sse_banded_LCS_alignment.c
+../../../src/obiblob.h
+../../../src/obiblob.c
+../../../src/utils.h
+../../../src/utils.c
+../../../src/obidms.h
+../../../src/obidms.c
+../../../src/libjson/json_utils.h
+../../../src/libjson/json_utils.c
+../../../src/libjson/cJSON.h
+../../../src/libjson/cJSON.c
+../../../src/obiavl.h
+../../../src/obiavl.c
+../../../src/bloom.h
+../../../src/bloom.c
+../../../src/crc64.h
+../../../src/crc64.c
+../../../src/murmurhash2.h
+../../../src/murmurhash2.c
+../../../src/obidmscolumn.h
+../../../src/obidmscolumn.c
+../../../src/obitypes.h
+../../../src/obitypes.c
+../../../src/obidmscolumndir.h
+../../../src/obidmscolumndir.c
+../../../src/obiblob_indexer.h
+../../../src/obiblob_indexer.c
+../../../src/obiview.h
+../../../src/obiview.c
+../../../src/hashtable.h
+../../../src/hashtable.c
+../../../src/linked_list.h
+../../../src/linked_list.c
+../../../src/obidmscolumn_array.h
+../../../src/obidmscolumn_array.c
+../../../src/obidmscolumn_blob.h
+../../../src/obidmscolumn_blob.c
+../../../src/obidmscolumn_idx.h
+../../../src/obidmscolumn_idx.c
+../../../src/obidmscolumn_bool.h
+../../../src/obidmscolumn_bool.c
+../../../src/obidmscolumn_char.h
+../../../src/obidmscolumn_char.c
+../../../src/obidmscolumn_float.h
+../../../src/obidmscolumn_float.c
+../../../src/obidmscolumn_int.h
+../../../src/obidmscolumn_int.c
+../../../src/obidmscolumn_qual.h
+../../../src/obidmscolumn_qual.c
+../../../src/obidmscolumn_seq.h
+../../../src/obidmscolumn_seq.c
+../../../src/obidmscolumn_str.h
+../../../src/obidmscolumn_str.c
+../../../src/array_indexer.h
+../../../src/array_indexer.c
+../../../src/char_str_indexer.h
+../../../src/char_str_indexer.c
+../../../src/dna_seq_indexer.h
+../../../src/dna_seq_indexer.c
+../../../src/encode.c
+../../../src/encode.h
+../../../src/uint8_indexer.c
+../../../src/uint8_indexer.h
+../../../src/build_reference_db.c
+../../../src/build_reference_db.h
+../../../src/kmer_similarity.c
+../../../src/kmer_similarity.h
+../../../src/obi_clean.c
+../../../src/obi_clean.h
+../../../src/obi_ecopcr.c
+../../../src/obi_ecopcr.h
+../../../src/obi_ecotag.c
+../../../src/obi_ecotag.h
+../../../src/obidms_taxonomy.c
+../../../src/obidms_taxonomy.h
+../../../src/obilittlebigman.c
+../../../src/obilittlebigman.h
+../../../src/_sse.h
+../../../src/obidebug.h
+../../../src/libecoPCR/libapat/CODES/dft_code.h
+../../../src/libecoPCR/libapat/CODES/dna_code.h
+../../../src/libecoPCR/libapat/CODES/prot_code.h
+../../../src/libecoPCR/libapat/apat_parse.c
+../../../src/libecoPCR/libapat/apat_search.c
+../../../src/libecoPCR/libapat/apat.h
+../../../src/libecoPCR/libapat/Gmach.h
+../../../src/libecoPCR/libapat/Gtypes.h
+../../../src/libecoPCR/libapat/libstki.c
+../../../src/libecoPCR/libapat/libstki.h
+../../../src/libecoPCR/libthermo/nnparams.h
+../../../src/libecoPCR/libthermo/nnparams.c
+../../../src/libecoPCR/ecoapat.c
+../../../src/libecoPCR/ecodna.c
+../../../src/libecoPCR/ecoError.c
+../../../src/libecoPCR/ecoMalloc.c
+../../../src/libecoPCR/ecoPCR.h
+
+
+
+
+
+
+

python/obitools3/apps/arguments.pxd

@@ -0,0 +1,3 @@
+#cython: language_level=3
+
+cpdef buildArgumentParser(str configname, str softname)

python/obitools3/apps/arguments.pyx

@@ -0,0 +1,62 @@
+#cython: language_level=3
+
+'''
+Created on 27 mars 2016
+
+@author: coissac
+'''
+
+import argparse
+import sys
+
+
+from .command import getCommandsList
+
+class ObiParser(argparse.ArgumentParser): 
+    def error(self, message):
+        sys.stderr.write('error: %s\n' % message)
+        self.print_help()
+        sys.exit(2)
+
+cpdef buildArgumentParser(str configname, 
+                          str softname):
+    parser = ObiParser()
+    
+    parser.add_argument('--version',   dest='%s:version' % configname, 
+                                       action='store_true', 
+                                       default=False, 
+                        help='Print the version of %s' % softname)
+
+    parser.add_argument('--log',       dest='%s:log' % configname, 
+                                       action='store',
+                                       type=str,
+                                       default=None, 
+                        help='Create a logfile')
+
+    parser.add_argument('--no-progress', dest='%s:progress' % configname, 
+                                       action='store_false', 
+                                       default=None, 
+                        help='Do not print the progress bar during analyzes')
+
+    subparsers = parser.add_subparsers(title='subcommands',
+                                       description='valid subcommands',
+                                       help='additional help')
+    
+    commands = getCommandsList()
+    
+    for c in commands:
+        module = commands[c]
+        
+        if hasattr(module, "run"):
+            if hasattr(module, "__title__"):
+                sub = subparsers.add_parser(c,help=module.__title__)
+            else:
+                sub = subparsers.add_parser(c)
+    
+            if hasattr(module, "addOptions"):
+                module.addOptions(sub)
+            
+            sub.set_defaults(**{'%s:module'  % configname : module})
+            sub.set_defaults(**{'%s:modulename'  % configname : c})
+              
+    return parser

python/obitools3/apps/command.cfiles

@@ -0,0 +1,110 @@
+../../../src/obi_lcs.h
+../../../src/obi_lcs.c
+../../../src/obierrno.h
+../../../src/obierrno.c
+../../../src/upperband.h
+../../../src/upperband.c
+../../../src/sse_banded_LCS_alignment.h
+../../../src/sse_banded_LCS_alignment.c
+../../../src/obiblob.h
+../../../src/obiblob.c
+../../../src/utils.h
+../../../src/utils.c
+../../../src/obidms.h
+../../../src/obidms.c
+../../../src/libjson/json_utils.h
+../../../src/libjson/json_utils.c
+../../../src/libjson/cJSON.h
+../../../src/libjson/cJSON.c
+../../../src/obiavl.h
+../../../src/obiavl.c
+../../../src/bloom.h
+../../../src/bloom.c
+../../../src/crc64.h
+../../../src/crc64.c
+../../../src/murmurhash2.h
+../../../src/murmurhash2.c
+../../../src/obidmscolumn.h
+../../../src/obidmscolumn.c
+../../../src/obitypes.h
+../../../src/obitypes.c
+../../../src/obidmscolumndir.h
+../../../src/obidmscolumndir.c
+../../../src/obiblob_indexer.h
+../../../src/obiblob_indexer.c
+../../../src/obiview.h
+../../../src/obiview.c
+../../../src/hashtable.h
+../../../src/hashtable.c
+../../../src/linked_list.h
+../../../src/linked_list.c
+../../../src/obidmscolumn_array.h
+../../../src/obidmscolumn_array.c
+../../../src/obidmscolumn_blob.h
+../../../src/obidmscolumn_blob.c
+../../../src/obidmscolumn_idx.h
+../../../src/obidmscolumn_idx.c
+../../../src/obidmscolumn_bool.h
+../../../src/obidmscolumn_bool.c
+../../../src/obidmscolumn_char.h
+../../../src/obidmscolumn_char.c
+../../../src/obidmscolumn_float.h
+../../../src/obidmscolumn_float.c
+../../../src/obidmscolumn_int.h
+../../../src/obidmscolumn_int.c
+../../../src/obidmscolumn_qual.h
+../../../src/obidmscolumn_qual.c
+../../../src/obidmscolumn_seq.h
+../../../src/obidmscolumn_seq.c
+../../../src/obidmscolumn_str.h
+../../../src/obidmscolumn_str.c
+../../../src/array_indexer.h
+../../../src/array_indexer.c
+../../../src/char_str_indexer.h
+../../../src/char_str_indexer.c
+../../../src/dna_seq_indexer.h
+../../../src/dna_seq_indexer.c
+../../../src/encode.c
+../../../src/encode.h
+../../../src/uint8_indexer.c
+../../../src/uint8_indexer.h
+../../../src/build_reference_db.c
+../../../src/build_reference_db.h
+../../../src/kmer_similarity.c
+../../../src/kmer_similarity.h
+../../../src/obi_clean.c
+../../../src/obi_clean.h
+../../../src/obi_ecopcr.c
+../../../src/obi_ecopcr.h
+../../../src/obi_ecotag.c
+../../../src/obi_ecotag.h
+../../../src/obidms_taxonomy.c
+../../../src/obidms_taxonomy.h
+../../../src/obilittlebigman.c
+../../../src/obilittlebigman.h
+../../../src/_sse.h
+../../../src/obidebug.h
+../../../src/libecoPCR/libapat/CODES/dft_code.h
+../../../src/libecoPCR/libapat/CODES/dna_code.h
+../../../src/libecoPCR/libapat/CODES/prot_code.h
+../../../src/libecoPCR/libapat/apat_parse.c
+../../../src/libecoPCR/libapat/apat_search.c
+../../../src/libecoPCR/libapat/apat.h
+../../../src/libecoPCR/libapat/Gmach.h
+../../../src/libecoPCR/libapat/Gtypes.h
+../../../src/libecoPCR/libapat/libstki.c
+../../../src/libecoPCR/libapat/libstki.h
+../../../src/libecoPCR/libthermo/nnparams.h
+../../../src/libecoPCR/libthermo/nnparams.c
+../../../src/libecoPCR/ecoapat.c
+../../../src/libecoPCR/ecodna.c
+../../../src/libecoPCR/ecoError.c
+../../../src/libecoPCR/ecoMalloc.c
+../../../src/libecoPCR/ecoPCR.h
+
+
+
+
+
+
+

python/obitools3/apps/command.pxd

@@ -0,0 +1,3 @@
+#cython: language_level=3
+
+cdef object loadCommand(str name,loader)

python/obitools3/apps/command.pyx

@@ -0,0 +1,44 @@
+#cython: language_level=3
+
+'''
+Created on 27 mars 2016
+
+@author: coissac
+'''
+
+import pkgutil
+
+from obitools3 import commands
+
+cdef object loadCommand(str name,loader):
+    '''
+    Load a command module from its name and an ImpLoader
+    
+    This function is for internal use
+    
+    @param name:   name of the module
+    @type name: str 
+    @param loader: the module loader
+    @type loader: ImpLoader
+    
+    @return the loaded module
+    @rtype: module 
+    '''
+    
+    module = loader.find_module(name).load_module(name)
+    return module
+
+def getCommandsList():
+    '''
+    Returns the list of sub-commands available to the main `obi` command
+    
+    @return: a dict instance with key corresponding to each command and
+             value corresponding to the module
+             
+    @rtype: dict
+    '''
+    
+    cdef dict cmds = dict((x[1],loadCommand(x[1],x[0])) 
+                           for x in pkgutil.iter_modules(commands.__path__) 
+                           if not x[2])
+    return cmds

python/obitools3/apps/config.cfiles

@@ -0,0 +1,110 @@
+../../../src/obi_lcs.h
+../../../src/obi_lcs.c
+../../../src/obierrno.h
+../../../src/obierrno.c
+../../../src/upperband.h
+../../../src/upperband.c
+../../../src/sse_banded_LCS_alignment.h
+../../../src/sse_banded_LCS_alignment.c
+../../../src/obiblob.h
+../../../src/obiblob.c
+../../../src/utils.h
+../../../src/utils.c
+../../../src/obidms.h
+../../../src/obidms.c
+../../../src/libjson/json_utils.h
+../../../src/libjson/json_utils.c
+../../../src/libjson/cJSON.h
+../../../src/libjson/cJSON.c
+../../../src/obiavl.h
+../../../src/obiavl.c
+../../../src/bloom.h
+../../../src/bloom.c
+../../../src/crc64.h
+../../../src/crc64.c
+../../../src/murmurhash2.h
+../../../src/murmurhash2.c
+../../../src/obidmscolumn.h
+../../../src/obidmscolumn.c
+../../../src/obitypes.h
+../../../src/obitypes.c
+../../../src/obidmscolumndir.h
+../../../src/obidmscolumndir.c
+../../../src/obiblob_indexer.h
+../../../src/obiblob_indexer.c
+../../../src/obiview.h
+../../../src/obiview.c
+../../../src/hashtable.h
+../../../src/hashtable.c
+../../../src/linked_list.h
+../../../src/linked_list.c
+../../../src/obidmscolumn_array.h
+../../../src/obidmscolumn_array.c
+../../../src/obidmscolumn_blob.h
+../../../src/obidmscolumn_blob.c
+../../../src/obidmscolumn_idx.h
+../../../src/obidmscolumn_idx.c
+../../../src/obidmscolumn_bool.h
+../../../src/obidmscolumn_bool.c
+../../../src/obidmscolumn_char.h
+../../../src/obidmscolumn_char.c
+../../../src/obidmscolumn_float.h
+../../../src/obidmscolumn_float.c
+../../../src/obidmscolumn_int.h
+../../../src/obidmscolumn_int.c
+../../../src/obidmscolumn_qual.h
+../../../src/obidmscolumn_qual.c
+../../../src/obidmscolumn_seq.h
+../../../src/obidmscolumn_seq.c
+../../../src/obidmscolumn_str.h
+../../../src/obidmscolumn_str.c
+../../../src/array_indexer.h
+../../../src/array_indexer.c
+../../../src/char_str_indexer.h
+../../../src/char_str_indexer.c
+../../../src/dna_seq_indexer.h
+../../../src/dna_seq_indexer.c
+../../../src/encode.c
+../../../src/encode.h
+../../../src/uint8_indexer.c
+../../../src/uint8_indexer.h
+../../../src/build_reference_db.c
+../../../src/build_reference_db.h
+../../../src/kmer_similarity.c
+../../../src/kmer_similarity.h
+../../../src/obi_clean.c
+../../../src/obi_clean.h
+../../../src/obi_ecopcr.c
+../../../src/obi_ecopcr.h
+../../../src/obi_ecotag.c
+../../../src/obi_ecotag.h
+../../../src/obidms_taxonomy.c
+../../../src/obidms_taxonomy.h
+../../../src/obilittlebigman.c
+../../../src/obilittlebigman.h
+../../../src/_sse.h
+../../../src/obidebug.h
+../../../src/libecoPCR/libapat/CODES/dft_code.h
+../../../src/libecoPCR/libapat/CODES/dna_code.h
+../../../src/libecoPCR/libapat/CODES/prot_code.h
+../../../src/libecoPCR/libapat/apat_parse.c
+../../../src/libecoPCR/libapat/apat_search.c
+../../../src/libecoPCR/libapat/apat.h
+../../../src/libecoPCR/libapat/Gmach.h
+../../../src/libecoPCR/libapat/Gtypes.h
+../../../src/libecoPCR/libapat/libstki.c
+../../../src/libecoPCR/libapat/libstki.h
+../../../src/libecoPCR/libthermo/nnparams.h
+../../../src/libecoPCR/libthermo/nnparams.c
+../../../src/libecoPCR/ecoapat.c
+../../../src/libecoPCR/ecodna.c
+../../../src/libecoPCR/ecoError.c
+../../../src/libecoPCR/ecoMalloc.c
+../../../src/libecoPCR/ecoPCR.h
+
+
+
+
+
+
+

python/obitools3/apps/config.pxd

@@ -0,0 +1,10 @@
+#cython: language_level=3
+
+cpdef str setRootConfigName(str rootname)
+cpdef str getRootConfigName()
+
+cdef dict buildDefaultConfiguration(str root_config_name,
+                                    dict  config)
+
+cpdef dict getConfiguration(str root_config_name=?,
+                                    dict  config=?)

python/obitools3/apps/config.pyx

@@ -0,0 +1,114 @@
+#cython: language_level=3
+
+'''
+Created on 27 mars 2016
+
+@author: coissac
+'''
+
+import sys
+
+from .command   import  getCommandsList
+from .logging   cimport getLogger
+from .arguments cimport buildArgumentParser
+
+from ..version import version
+from _curses import version
+
+cdef dict __default_config__ = {}
+
+
+cpdef str setRootConfigName(str rootname):
+    global __default_config__
+    if '__root_config__' in __default_config__:
+        if __default_config__["__root_config__"] in __default_config__:
+            __default_config__[rootname]=__default_config__[__default_config__["__root_config__"]]
+            del __default_config__[__default_config__["__root_config__"]]
+    __default_config__['__root_config__']=rootname
+    return rootname
+
+cpdef str getRootConfigName():
+    global __default_config__
+    return __default_config__.get('__root_config__',None)
+
+cdef dict buildDefaultConfiguration(str root_config_name,
+                                    dict  config):
+    global __default_config__
+    
+    __default_config__.clear()
+    setRootConfigName(root_config_name)    
+
+    __default_config__[root_config_name]=config
+    
+    config['version']=version
+    
+    commands = getCommandsList()
+    
+    for c in commands:
+        module = commands[c]
+    
+        assert hasattr(module, "run")
+        
+        if hasattr(module, 'default_config'):
+            __default_config__[c]=module.default_config
+        else:
+            __default_config__[c]={}
+                        
+    return __default_config__
+        
+
+cpdef dict getConfiguration(str root_config_name="__default__",
+                            dict  config={}):
+    global __default_config__
+
+    if '__done__' in __default_config__:
+        return __default_config__
+    
+    if root_config_name=="__default__":
+        raise RuntimeError("No root_config_name specified")
+    
+    if not config:
+        raise RuntimeError("Base configuration is empty")
+    
+    
+    
+    config =  buildDefaultConfiguration(root_config_name,
+                                        config)
+    
+    parser = buildArgumentParser(root_config_name,
+                                 config[root_config_name]['software'])
+    
+    options = vars(parser.parse_args())
+
+    if options['%s:version' % root_config_name]:
+        print("%s - Version %s" % (config[root_config_name]['software'],
+                                   config[root_config_name]['version']))
+        sys.exit(0)
+    
+    for k in options:
+        section,key = k.split(':')
+        s = config[section]
+        if options[k] is not None:
+            s[key]=options[k]
+            
+    if not 'module' in config[root_config_name]:
+        print('\nError: No command specified',file=sys.stderr)
+        parser.print_help()
+        sys.exit(2)
+                
+    getLogger(config)
+    
+    config['__done__']=True
+            
+    return config
+
+def logger(level, *messages):
+    try:
+        config=getConfiguration()
+        root = config["__root_config__"]
+        l = config[root]['logger']
+        if config[root]['verbose']:
+            getattr(l, level)(*messages)
+    except:
+        print(*messages,file=sys.stderr)
+

python/obitools3/apps/logging.cfiles

@@ -0,0 +1,110 @@
+../../../src/obi_lcs.h
+../../../src/obi_lcs.c
+../../../src/obierrno.h
+../../../src/obierrno.c
+../../../src/upperband.h
+../../../src/upperband.c
+../../../src/sse_banded_LCS_alignment.h
+../../../src/sse_banded_LCS_alignment.c
+../../../src/obiblob.h
+../../../src/obiblob.c
+../../../src/utils.h
+../../../src/utils.c
+../../../src/obidms.h
+../../../src/obidms.c
+../../../src/libjson/json_utils.h
+../../../src/libjson/json_utils.c
+../../../src/libjson/cJSON.h
+../../../src/libjson/cJSON.c
+../../../src/obiavl.h
+../../../src/obiavl.c
+../../../src/bloom.h
+../../../src/bloom.c
+../../../src/crc64.h
+../../../src/crc64.c
+../../../src/murmurhash2.h
+../../../src/murmurhash2.c
+../../../src/obidmscolumn.h
+../../../src/obidmscolumn.c
+../../../src/obitypes.h
+../../../src/obitypes.c
+../../../src/obidmscolumndir.h
+../../../src/obidmscolumndir.c
+../../../src/obiblob_indexer.h
+../../../src/obiblob_indexer.c
+../../../src/obiview.h
+../../../src/obiview.c
+../../../src/hashtable.h
+../../../src/hashtable.c
+../../../src/linked_list.h
+../../../src/linked_list.c
+../../../src/obidmscolumn_array.h
+../../../src/obidmscolumn_array.c
+../../../src/obidmscolumn_blob.h
+../../../src/obidmscolumn_blob.c
+../../../src/obidmscolumn_idx.h
+../../../src/obidmscolumn_idx.c
+../../../src/obidmscolumn_bool.h
+../../../src/obidmscolumn_bool.c
+../../../src/obidmscolumn_char.h
+../../../src/obidmscolumn_char.c
+../../../src/obidmscolumn_float.h
+../../../src/obidmscolumn_float.c
+../../../src/obidmscolumn_int.h
+../../../src/obidmscolumn_int.c
+../../../src/obidmscolumn_qual.h
+../../../src/obidmscolumn_qual.c
+../../../src/obidmscolumn_seq.h
+../../../src/obidmscolumn_seq.c
+../../../src/obidmscolumn_str.h
+../../../src/obidmscolumn_str.c
+../../../src/array_indexer.h
+../../../src/array_indexer.c
+../../../src/char_str_indexer.h
+../../../src/char_str_indexer.c
+../../../src/dna_seq_indexer.h
+../../../src/dna_seq_indexer.c
+../../../src/encode.c
+../../../src/encode.h
+../../../src/uint8_indexer.c
+../../../src/uint8_indexer.h
+../../../src/build_reference_db.c
+../../../src/build_reference_db.h
+../../../src/kmer_similarity.c
+../../../src/kmer_similarity.h
+../../../src/obi_clean.c
+../../../src/obi_clean.h
+../../../src/obi_ecopcr.c
+../../../src/obi_ecopcr.h
+../../../src/obi_ecotag.c
+../../../src/obi_ecotag.h
+../../../src/obidms_taxonomy.c
+../../../src/obidms_taxonomy.h
+../../../src/obilittlebigman.c
+../../../src/obilittlebigman.h
+../../../src/_sse.h
+../../../src/obidebug.h
+../../../src/libecoPCR/libapat/CODES/dft_code.h
+../../../src/libecoPCR/libapat/CODES/dna_code.h
+../../../src/libecoPCR/libapat/CODES/prot_code.h
+../../../src/libecoPCR/libapat/apat_parse.c
+../../../src/libecoPCR/libapat/apat_search.c
+../../../src/libecoPCR/libapat/apat.h
+../../../src/libecoPCR/libapat/Gmach.h
+../../../src/libecoPCR/libapat/Gtypes.h
+../../../src/libecoPCR/libapat/libstki.c
+../../../src/libecoPCR/libapat/libstki.h
+../../../src/libecoPCR/libthermo/nnparams.h
+../../../src/libecoPCR/libthermo/nnparams.c
+../../../src/libecoPCR/ecoapat.c
+../../../src/libecoPCR/ecodna.c
+../../../src/libecoPCR/ecoError.c
+../../../src/libecoPCR/ecoMalloc.c
+../../../src/libecoPCR/ecoPCR.h
+
+
+
+
+
+
+

python/obitools3/apps/logging.pxd

@@ -0,0 +1,3 @@
+#cython: language_level=3
+
+cpdef getLogger(dict config)

python/obitools3/apps/logging.pyx

@@ -0,0 +1,48 @@
+#cython: language_level=3
+
+'''
+Created on 27 mars 2016
+
+@author: coissac
+'''
+
+import logging
+import sys
+
+cpdef getLogger(dict config):
+    '''
+    Returns the logger as defined by the command line option
+    or by the config file
+    :param config:
+    '''
+    
+    root = config["__root_config__"]
+ 
+    level  = config[root]['loglevel'] 
+    logfile= config[root]['log'] 
+    
+    rootlogger   = logging.getLogger()
+    logFormatter = logging.Formatter("%%(asctime)s [%s : %%(levelname)-5.5s]  %%(message)s" % config[root]['modulename'])
+
+    stderrHandler = logging.StreamHandler(sys.stderr)
+    stderrHandler.setFormatter(logFormatter)
+
+    rootlogger.addHandler(stderrHandler)
+    
+    if logfile:
+        fileHandler = logging.FileHandler(logfile)
+        fileHandler.setFormatter(logFormatter)
+        rootlogger.addHandler(fileHandler)
+    
+    try:
+        loglevel = getattr(logging, level) 
+    except:
+        loglevel = logging.INFO
+        
+    rootlogger.setLevel(loglevel)
+    
+    config[root]['logger']=rootlogger
+    config[root]['verbose']=True
+        
+    return rootlogger
+

python/obitools3/apps/optiongroups/__init__.py

@@ -0,0 +1,272 @@
+def __addInputOption(optionManager):
+    
+    optionManager.add_argument(
+                    dest='obi:inputURI',  
+                    metavar='INPUT', 
+                    help='Data source URI')
+    
+
+    group = optionManager.add_argument_group("Restriction to a sub-part options",
+                    "Allows to limit analysis to a sub-part of the input")
+
+    group.add_argument('--skip',
+                     action="store", dest="obi:skip",
+                     metavar='<N>',
+                     default=None,
+                     type=int,
+                     help="skip the N first sequences")
+
+    group.add_argument('--only',
+                     action="store", dest="obi:only",
+                     metavar='<N>',
+                     default=None,
+                     type=int,
+                     help="treat only N sequences")
+    
+
+def __addImportInputOption(optionManager):
+    group = optionManager.add_argument_group("Input format options for imported files")
+
+    group.add_argument('--fasta-input',
+                     action="store_const", dest="obi:inputformat",
+                     default=None,
+                     const=b'fasta',
+                     help="Input file is in sanger fasta format")
+
+    group.add_argument('--fastq-input',
+                     action="store_const", dest="obi:inputformat",
+                     default=None,
+                     const=b'fastq',
+                     help="Input file is in fastq format")
+
+    group.add_argument('--embl-input',
+                     action="store_const", dest="obi:inputformat",
+                     default=None,
+                     const=b'embl',
+                     help="Input file is in embl nucleic format")
+
+    group.add_argument('--genbank-input',
+                     action="store_const", dest="obi:inputformat",
+                     default=None,
+                     const=b'genbank',
+                     help="Input file is in genbank nucleic format")
+
+    group.add_argument('--ngsfilter-input',
+                     action="store_const", dest="obi:inputformat",
+                     default=None,
+                     const=b'ngsfilter',
+                     help="Input file is an ngsfilter file")
+
+    group.add_argument('--ecopcr-result-input',
+                     action="store_const", dest="obi:inputformat",
+                     default=None,
+                     const=b'ecopcr',
+                     help="Input file is the result of an ecoPCR (version 2)")
+
+    group.add_argument('--ecoprimers-result-input',
+                     action="store_const", dest="obi:inputformat",
+                     default=None,
+                     const=b'ecoprimers',
+                     help="Input file is the result of an ecoprimers")
+
+    group.add_argument('--tabular-input',
+                     action="store_const", dest="obi:inputformat",
+                     default=None,
+                     const=b'tabular',
+                     help="Input file is a tabular file")
+
+    group.add_argument('--no-skip-on-error',
+                     action="store_false", dest="obi:skiperror",
+                     default=True,
+                     help="Don't skip sequence entries with parsing errors (default: they are skipped)")
+
+    group.add_argument('--no-quality',
+                     action="store_true", dest="obi:noquality",
+                     default=False,
+                     help="Do not import fastQ quality")
+
+    group.add_argument('--quality-sanger',
+                     action="store_const", dest="obi:qualityformat",
+                     default=None,
+                     const=b'sanger',
+                     help="Fastq quality is encoded following sanger format (standard fastq)")
+
+    group.add_argument('--quality-solexa',
+                     action="store_const", dest="obi:qualityformat",
+                     default=None,
+                     const=b'solexa',
+                     help="Fastq quality is encoded following solexa sequencer format")
+
+    group.add_argument('--nuc',
+                     action="store_const", dest="obi:moltype",
+                     default=None,
+                     const=b'nuc',
+                     help="Input file contains nucleic sequences")
+    
+    group.add_argument('--prot',
+                     action="store_const", dest="obi:moltype",
+                     default=None,
+                     const=b'pep',
+                     help="Input file contains protein sequences")
+
+    group.add_argument('--input-na-string',
+                     action="store", dest="obi:inputnastring",
+                     default="NA",
+                     type=str,
+                     help="String associated with Non Available (NA) values in the input")
+
+  
+def __addTabularInputOption(optionManager):
+    group = optionManager.add_argument_group("Input format options for tabular files")
+
+    group.add_argument('--header',
+                     action="store_true", dest="obi:header",
+                     default=False,
+                     help="First line of tabular file contains column names")
+
+    group.add_argument('--sep',
+                     action="store", dest="obi:sep",
+                     default=None,
+                     type=str,
+                     help="Column separator")
+    
+    group.add_argument('--dec',
+                     action="store", dest="obi:dec",
+                     default=".",
+                     type=str,
+                     help="Decimal separator")
+    
+    group.add_argument('--strip-white',
+                     action="store_false", dest="obi:stripwhite",
+                     default=True,
+                     help="Remove white chars at the beginning and the end of values")
+
+    group.add_argument('--blank-line-skip',
+                     action="store_false", dest="obi:blanklineskip",
+                     default=True,
+                     help="Skip empty lines")
+
+    group.add_argument('--comment-char',
+                     action="store", dest="obi:commentchar",
+                     default="#",
+                     type=str,
+                     help="Lines starting by this char are considered as comment")
+
+
+def __addTaxdumpInputOption(optionManager):  # TODO maybe not the best way to do it
+    group = optionManager.add_argument_group("Input format options for taxdump")
+
+    group.add_argument('--taxdump',
+                     action="store_true", dest="obi:taxdump",
+                     default=False,
+                     help="Whether the input is a taxdump")
+
+
+def __addTaxonomyOption(optionManager):
+    group = optionManager.add_argument_group("Input format options for taxonomy")
+
+    group.add_argument('--taxonomy',
+                     action="store", dest="obi:taxoURI",
+                     default=None,
+                     help="Taxonomy URI")
+    
+    #TODO option bool to download taxo if URI doesn't exist
+
+
+def addMinimalInputOption(optionManager):
+    __addInputOption(optionManager)
+
+    
+def addImportInputOption(optionManager):
+    __addInputOption(optionManager)
+    __addImportInputOption(optionManager)
+
+
+def addTabularInputOption(optionManager):
+    __addTabularInputOption(optionManager)
+
+
+def addTaxonomyOption(optionManager):
+    __addTaxonomyOption(optionManager)
+
+
+def addTaxdumpInputOption(optionManager):
+    __addTaxdumpInputOption(optionManager)
+
+
+def addAllInputOption(optionManager):
+    __addInputOption(optionManager)
+    __addImportInputOption(optionManager)
+    __addTabularInputOption(optionManager)
+    __addTaxonomyOption(optionManager)
+    __addTaxdumpInputOption(optionManager)    
+
+
+def __addOutputOption(optionManager):
+    
+    optionManager.add_argument(
+                    dest='obi:outputURI',  
+                    metavar='OUTPUT', 
+                    help='Data destination URI')
+
+
+def __addDMSOutputOption(optionManager):
+    group = optionManager.add_argument_group("Output options for DMS data")
+
+    group.add_argument('--no-create-dms',
+                 action="store_true", dest="obi:nocreatedms",
+                 default=False,
+                 help="Don't create an output DMS is it is not existing")
+
+    group.add_argument('--max-elts',
+                 action="store", dest="obi:maxelts",
+                 metavar='<N>',
+                 default=1000,
+                 type=int,
+                 help="Maximum number of elements per line in a column "
+                      "(e.g. the number of different keys in a dictionary-type "
+                      "key from sequence headers). If the number of different keys "
+                      "is greater than N, the values are stored as character strings")
+
+
+def __addExportOutputOption(optionManager):
+    group = optionManager.add_argument_group("Output format options for exported files")
+
+    group.add_argument('--fasta-output',
+                     action="store_const", dest="obi:outputformat",
+                     default=None,
+                     const=b'fasta',
+                     help="Output file is in sanger fasta format")
+
+    group.add_argument('--fastq-output',
+                     action="store_const", dest="obi:outputformat",
+                     default=None,
+                     const=b'fastq',
+                     help="Output file is in fastq format")
+
+    group.add_argument('--print-na',
+                     action="store_true", dest="obi:printna",
+                     default=False,
+                     help="Print Non Available (NA) values in the output")
+
+    group.add_argument('--output-na-string',
+                     action="store", dest="obi:outputnastring",
+                     default="NA",
+                     type=str,
+                     help="String associated with Non Available (NA) values in the output")
+
+
+def addMinimalOutputOption(optionManager):
+    __addOutputOption(optionManager)
+    __addDMSOutputOption(optionManager)
+
+def addExportOutputOption(optionManager):
+    __addOutputOption(optionManager)
+    __addExportOutputOption(optionManager)
+
+
+def addAllOutputOption(optionManager):
+    __addOutputOption(optionManager)
+    __addDMSOutputOption(optionManager)
+    __addExportOutputOption(optionManager)
+

python/obitools3/apps/progress.cfiles

@@ -0,0 +1,110 @@
+../../../src/obi_lcs.h
+../../../src/obi_lcs.c
+../../../src/obierrno.h
+../../../src/obierrno.c
+../../../src/upperband.h
+../../../src/upperband.c
+../../../src/sse_banded_LCS_alignment.h
+../../../src/sse_banded_LCS_alignment.c
+../../../src/obiblob.h
+../../../src/obiblob.c
+../../../src/utils.h
+../../../src/utils.c
+../../../src/obidms.h
+../../../src/obidms.c
+../../../src/libjson/json_utils.h
+../../../src/libjson/json_utils.c
+../../../src/libjson/cJSON.h
+../../../src/libjson/cJSON.c
+../../../src/obiavl.h
+../../../src/obiavl.c
+../../../src/bloom.h
+../../../src/bloom.c
+../../../src/crc64.h
+../../../src/crc64.c
+../../../src/murmurhash2.h
+../../../src/murmurhash2.c
+../../../src/obidmscolumn.h
+../../../src/obidmscolumn.c
+../../../src/obitypes.h
+../../../src/obitypes.c
+../../../src/obidmscolumndir.h
+../../../src/obidmscolumndir.c
+../../../src/obiblob_indexer.h
+../../../src/obiblob_indexer.c
+../../../src/obiview.h
+../../../src/obiview.c
+../../../src/hashtable.h
+../../../src/hashtable.c
+../../../src/linked_list.h
+../../../src/linked_list.c
+../../../src/obidmscolumn_array.h
+../../../src/obidmscolumn_array.c
+../../../src/obidmscolumn_blob.h
+../../../src/obidmscolumn_blob.c
+../../../src/obidmscolumn_idx.h
+../../../src/obidmscolumn_idx.c
+../../../src/obidmscolumn_bool.h
+../../../src/obidmscolumn_bool.c
+../../../src/obidmscolumn_char.h
+../../../src/obidmscolumn_char.c
+../../../src/obidmscolumn_float.h
+../../../src/obidmscolumn_float.c
+../../../src/obidmscolumn_int.h
+../../../src/obidmscolumn_int.c
+../../../src/obidmscolumn_qual.h
+../../../src/obidmscolumn_qual.c
+../../../src/obidmscolumn_seq.h
+../../../src/obidmscolumn_seq.c
+../../../src/obidmscolumn_str.h
+../../../src/obidmscolumn_str.c
+../../../src/array_indexer.h
+../../../src/array_indexer.c
+../../../src/char_str_indexer.h
+../../../src/char_str_indexer.c
+../../../src/dna_seq_indexer.h
+../../../src/dna_seq_indexer.c
+../../../src/encode.c
+../../../src/encode.h
+../../../src/uint8_indexer.c
+../../../src/uint8_indexer.h
+../../../src/build_reference_db.c
+../../../src/build_reference_db.h
+../../../src/kmer_similarity.c
+../../../src/kmer_similarity.h
+../../../src/obi_clean.c
+../../../src/obi_clean.h
+../../../src/obi_ecopcr.c
+../../../src/obi_ecopcr.h
+../../../src/obi_ecotag.c
+../../../src/obi_ecotag.h
+../../../src/obidms_taxonomy.c
+../../../src/obidms_taxonomy.h
+../../../src/obilittlebigman.c
+../../../src/obilittlebigman.h
+../../../src/_sse.h
+../../../src/obidebug.h
+../../../src/libecoPCR/libapat/CODES/dft_code.h
+../../../src/libecoPCR/libapat/CODES/dna_code.h
+../../../src/libecoPCR/libapat/CODES/prot_code.h
+../../../src/libecoPCR/libapat/apat_parse.c
+../../../src/libecoPCR/libapat/apat_search.c
+../../../src/libecoPCR/libapat/apat.h
+../../../src/libecoPCR/libapat/Gmach.h
+../../../src/libecoPCR/libapat/Gtypes.h
+../../../src/libecoPCR/libapat/libstki.c
+../../../src/libecoPCR/libapat/libstki.h
+../../../src/libecoPCR/libthermo/nnparams.h
+../../../src/libecoPCR/libthermo/nnparams.c
+../../../src/libecoPCR/ecoapat.c
+../../../src/libecoPCR/ecodna.c
+../../../src/libecoPCR/ecoError.c
+../../../src/libecoPCR/ecoMalloc.c
+../../../src/libecoPCR/ecoPCR.h
+
+
+
+
+
+
+

python/obitools3/apps/progress.pxd

@@ -0,0 +1,65 @@
+#cython: language_level=3
+
+cdef extern from "stdio.h":
+    struct FILE
+    int fprintf(FILE *stream, char *format, ...)
+    int fputs(char *string, FILE *stream)
+    FILE* stderr
+    ctypedef unsigned int off_t "unsigned long long"
+    
+cdef extern from "unistd.h":
+    int fsync(int fd);
+
+cdef extern from "time.h":
+    struct tm :
+        int tm_yday 
+        int tm_hour
+        int tm_min
+        int tm_sec
+
+    enum: CLOCKS_PER_SEC
+    
+    ctypedef int time_t
+    ctypedef int clock_t
+    ctypedef int suseconds_t
+    
+    struct timeval:
+        time_t      tv_sec     #  seconds */
+        suseconds_t tv_usec    #  microseconds */
+
+
+    struct timezone :
+        int tz_minuteswest;    # minutes west of Greenwich
+        int tz_dsttime;        # type of DST correction 
+
+        
+    int gettimeofday(timeval *tv, timezone *tz)
+
+
+    tm *gmtime_r(time_t *clock, tm *result)
+    time_t time(time_t *tloc)
+    clock_t clock()
+
+cdef class ProgressBar:
+    cdef off_t   maxi
+    cdef clock_t starttime
+    cdef clock_t lasttime
+    cdef clock_t tickcount
+    cdef int freq
+    cdef int cycle
+    cdef int arrow
+    cdef int lastlog
+    cdef bint ontty
+    cdef int fd
+    cdef bint cut
+    
+    cdef bytes _head
+    cdef char *chead
+    
+    cdef object logger
+
+    cdef char  *wheel
+    cdef char  *spaces
+    cdef char*  diese 
+    
+    cdef clock_t clock(self)

python/obitools3/apps/progress.pyx

@@ -0,0 +1,157 @@
+#cython: language_level=3
+
+'''
+Created on 27 mars 2016
+
+@author: coissac
+'''
+
+
+from ..utils cimport str2bytes, bytes2str
+from .config cimport getConfiguration 
+import sys
+
+
+cdef class ProgressBar:
+    
+    cdef clock_t clock(self):
+        cdef clock_t t
+        cdef timeval tp
+        cdef clock_t s
+        
+        <void> gettimeofday(&tp,NULL)
+        s = <clock_t> (<double> tp.tv_usec * 1.e-6 * <double> CLOCKS_PER_SEC)
+        t = tp.tv_sec * CLOCKS_PER_SEC + s 
+        
+        return t
+
+
+    def __init__(self,
+                 off_t maxi,
+                 dict  config={},
+                 str head="",
+                 double seconde=0.1,
+                 cut=False):
+        
+        self.starttime = self.clock()
+        self.lasttime  = self.starttime
+        self.tickcount = <clock_t> (seconde * CLOCKS_PER_SEC)
+        self.freq      = 1
+        self.cycle     = 0
+        self.arrow     = 0
+        self.lastlog   = 0
+        
+        if not config:
+            config=getConfiguration()
+        
+        self.ontty = sys.stderr.isatty()
+        
+        if (maxi<=0):
+            maxi=1
+            
+        self.maxi  = maxi
+        self.head  = head
+        self.chead = self._head 
+        self.cut   = cut
+        
+        self.logger=config[config["__root_config__"]]["logger"]
+        self.wheel =  '|/-\\'
+        self.spaces='          ' \
+                    '          ' \
+                    '          ' \
+                    '          ' \
+                    '          '
+        self.diese ='##########' \
+                    '##########' \
+                    '##########' \
+                    '##########' \
+                    '##########'  
+                          
+             
+    def __call__(self, object pos, bint force=False):
+        cdef off_t    ipos
+        cdef clock_t  elapsed
+        cdef clock_t  newtime
+        cdef clock_t  delta
+        cdef clock_t  more 
+        cdef double   percent 
+        cdef tm remain
+        cdef int days,hour,minu,sec
+        cdef off_t fraction
+        cdef int twentyth
+        
+        self.cycle+=1
+    
+        if self.cycle % self.freq == 0 or force:
+            self.cycle=1
+            newtime  = self.clock()
+            delta         = newtime - self.lasttime
+            self.lasttime = newtime
+            elapsed       = newtime - self.starttime
+#            print(" ",delta,elapsed,elapsed/CLOCKS_PER_SEC,self.tickcount)
+            
+            if   delta < self.tickcount / 5 :
+                self.freq*=2
+            elif delta > self.tickcount * 5 and self.freq>1:
+                self.freq/=2
+                
+            
+            if callable(pos):
+                ipos=pos()
+            else:
+                ipos=pos
+                
+            if ipos==0:
+                ipos=1                
+
+            percent = <double>ipos/<double>self.maxi
+            more = <time_t>((<double>elapsed / percent * (1. - percent))/CLOCKS_PER_SEC)
+            <void>gmtime_r(&more, &remain)
+            days  = remain.tm_yday 
+            hour  = remain.tm_hour
+            minu  = remain.tm_min
+            sec   = remain.tm_sec
+                
+            if self.ontty:
+                fraction=<int>(percent * 50.)
+                self.arrow=(self.arrow+1) % 4
+            
+                if days:
+                    <void>fprintf(stderr,b'\r%s %5.1f %% |%.*s%c%.*s] remain : %d days %02d:%02d:%02d\033[K',
+                                    self.chead,
+                                    percent*100,
+                                    fraction,self.diese,
+                                    self.wheel[self.arrow],
+                                    50-fraction,self.spaces,
+                                    days,hour,minu,sec)
+                else:
+                    <void>fprintf(stderr,b'\r%s %5.1f %% |%.*s%c%.*s] remain : %02d:%02d:%02d\033[K',
+                                    self.chead,
+                                    percent*100.,
+                                    fraction,self.diese,
+                                    self.wheel[self.arrow],
+                                    50-fraction,self.spaces,
+                                    hour,minu,sec)
+
+            if self.cut:
+                tenth = int(percent * 10)
+                if tenth != self.lastlog:
+                    
+                    if self.ontty:
+                        <void>fputs(b'\n',stderr)
+                    
+                    self.logger.info('%s %5.1f %% remain : %02d:%02d:%02d\033[K' % (
+                                            bytes2str(self._head),
+                                            percent*100.,
+                                            hour,minu,sec))
+                    self.lastlog=tenth
+        else:
+            self.cycle+=1
+
+
+    property head:    
+        def __get__(self):
+            return self._head
+        def __set__(self,str value):
+            self._head=str2bytes(value)
+            self.chead=self._head

python/obitools3/apps/temp.cfiles

@@ -0,0 +1,110 @@
+../../../src/obi_lcs.h
+../../../src/obi_lcs.c
+../../../src/obierrno.h
+../../../src/obierrno.c
+../../../src/upperband.h
+../../../src/upperband.c
+../../../src/sse_banded_LCS_alignment.h
+../../../src/sse_banded_LCS_alignment.c
+../../../src/obiblob.h
+../../../src/obiblob.c
+../../../src/utils.h
+../../../src/utils.c
+../../../src/obidms.h
+../../../src/obidms.c
+../../../src/libjson/json_utils.h
+../../../src/libjson/json_utils.c
+../../../src/libjson/cJSON.h
+../../../src/libjson/cJSON.c
+../../../src/obiavl.h
+../../../src/obiavl.c
+../../../src/bloom.h
+../../../src/bloom.c
+../../../src/crc64.h
+../../../src/crc64.c
+../../../src/murmurhash2.h
+../../../src/murmurhash2.c
+../../../src/obidmscolumn.h
+../../../src/obidmscolumn.c
+../../../src/obitypes.h
+../../../src/obitypes.c
+../../../src/obidmscolumndir.h
+../../../src/obidmscolumndir.c
+../../../src/obiblob_indexer.h
+../../../src/obiblob_indexer.c
+../../../src/obiview.h
+../../../src/obiview.c
+../../../src/hashtable.h
+../../../src/hashtable.c
+../../../src/linked_list.h
+../../../src/linked_list.c
+../../../src/obidmscolumn_array.h
+../../../src/obidmscolumn_array.c
+../../../src/obidmscolumn_blob.h
+../../../src/obidmscolumn_blob.c
+../../../src/obidmscolumn_idx.h
+../../../src/obidmscolumn_idx.c
+../../../src/obidmscolumn_bool.h
+../../../src/obidmscolumn_bool.c
+../../../src/obidmscolumn_char.h
+../../../src/obidmscolumn_char.c
+../../../src/obidmscolumn_float.h
+../../../src/obidmscolumn_float.c
+../../../src/obidmscolumn_int.h
+../../../src/obidmscolumn_int.c
+../../../src/obidmscolumn_qual.h
+../../../src/obidmscolumn_qual.c
+../../../src/obidmscolumn_seq.h
+../../../src/obidmscolumn_seq.c
+../../../src/obidmscolumn_str.h
+../../../src/obidmscolumn_str.c
+../../../src/array_indexer.h
+../../../src/array_indexer.c
+../../../src/char_str_indexer.h
+../../../src/char_str_indexer.c
+../../../src/dna_seq_indexer.h
+../../../src/dna_seq_indexer.c
+../../../src/encode.c
+../../../src/encode.h
+../../../src/uint8_indexer.c
+../../../src/uint8_indexer.h
+../../../src/build_reference_db.c
+../../../src/build_reference_db.h
+../../../src/kmer_similarity.c
+../../../src/kmer_similarity.h
+../../../src/obi_clean.c
+../../../src/obi_clean.h
+../../../src/obi_ecopcr.c
+../../../src/obi_ecopcr.h
+../../../src/obi_ecotag.c
+../../../src/obi_ecotag.h
+../../../src/obidms_taxonomy.c
+../../../src/obidms_taxonomy.h
+../../../src/obilittlebigman.c
+../../../src/obilittlebigman.h
+../../../src/_sse.h
+../../../src/obidebug.h
+../../../src/libecoPCR/libapat/CODES/dft_code.h
+../../../src/libecoPCR/libapat/CODES/dna_code.h
+../../../src/libecoPCR/libapat/CODES/prot_code.h
+../../../src/libecoPCR/libapat/apat_parse.c
+../../../src/libecoPCR/libapat/apat_search.c
+../../../src/libecoPCR/libapat/apat.h
+../../../src/libecoPCR/libapat/Gmach.h
+../../../src/libecoPCR/libapat/Gtypes.h
+../../../src/libecoPCR/libapat/libstki.c
+../../../src/libecoPCR/libapat/libstki.h
+../../../src/libecoPCR/libthermo/nnparams.h
+../../../src/libecoPCR/libthermo/nnparams.c
+../../../src/libecoPCR/ecoapat.c
+../../../src/libecoPCR/ecodna.c
+../../../src/libecoPCR/ecoError.c
+../../../src/libecoPCR/ecoMalloc.c
+../../../src/libecoPCR/ecoPCR.h
+
+
+
+
+
+
+

python/obitools3/apps/temp.pxd

@@ -0,0 +1,8 @@
+#cython: language_level=3
+
+'''
+Created on 28 juillet 2017
+
+@author: coissac
+'''
+

python/obitools3/apps/temp.pyx

@@ -0,0 +1,99 @@
+#cython: language_level=3
+
+'''
+Created on 28 juillet 2017
+
+@author: coissac
+'''
+
+from os import environb,getpid
+from os.path import join, isdir
+from tempfile import TemporaryDirectory, _get_candidate_names
+from shutil import rmtree
+from atexit import register
+
+from obitools3.dms.dms import DMS
+
+from obitools3.apps.config import getConfiguration
+from obitools3.apps.config import logger
+
+from obitools3.dms.dms cimport DMS
+from obitools3.utils cimport tobytes,tostr
+
+cpdef get_temp_dir():
+    """
+    Returns a temporary directory object specific of this instance of obitools.
+    
+    This is an application function. It cannot be called out of an obi command.
+    It requires a valid configuration.
+    
+    If the function is called several time from the same obi session, the same
+    directory is returned.
+    
+    If the OBITMP environment variable exist, the temporary directory is created
+    inside this directory.
+    
+    The directory is automatically destroyed at the end of the end of the process.
+    
+        @return: a temporary python directory object.
+    """
+    cdef bytes tmpdirname
+    cdef dict config = getConfiguration()
+
+    root = config["__root_config__"]
+    
+    try:
+        return config[root]["tempdir"].name
+    except KeyError:
+        pass
+    
+    try:
+        basedir=environb[b'OBITMP']
+    except KeyError:
+        basedir=None
+    
+    tmp = TemporaryDirectory(dir=basedir)
+        
+    config[root]["tempdir"]=tmp
+    
+    return tmp.name
+ 
+cpdef get_temp_dir_name():
+    """
+    Returns the name of the  temporary directory object 
+    specific of this instance of obitools.
+    
+        @return: the name of the temporary directory.
+        
+        @see get_temp_dir
+    """
+    return get_temp_dir_name().name
+          
+               
+cpdef get_temp_dms():
+
+    cdef bytes tmpdirname                   # @DuplicatedSignature
+    cdef dict config = getConfiguration()   # @DuplicatedSignature
+    cdef DMS tmpdms
+    
+    root = config["__root_config__"]
+    
+    try:
+        return config[root]["tempdms"]
+    except KeyError:
+        pass
+
+    tmpdirname=get_temp_dir()
+        
+    tempname = join(tmpdirname,
+                    b"obi.%d.%s" % (getpid(),
+                                    tobytes(next(_get_candidate_names())))
+                   )
+        
+    tmpdms = DMS.new(tempname)
+    
+    config[root]["tempdms"]=tmpdms
+    
+    return tmpdms
+    
+    

python/obitools3/commands/align.cfiles

@@ -0,0 +1,103 @@
+../../../src/obi_lcs.h
+../../../src/obi_lcs.c
+../../../src/obierrno.h
+../../../src/obierrno.c
+../../../src/upperband.h
+../../../src/upperband.c
+../../../src/sse_banded_LCS_alignment.h
+../../../src/sse_banded_LCS_alignment.c
+../../../src/obiblob.h
+../../../src/obiblob.c
+../../../src/utils.h
+../../../src/utils.c
+../../../src/obidms.h
+../../../src/obidms.c
+../../../src/libjson/json_utils.h
+../../../src/libjson/json_utils.c
+../../../src/libjson/cJSON.h
+../../../src/libjson/cJSON.c
+../../../src/obiavl.h
+../../../src/obiavl.c
+../../../src/bloom.h
+../../../src/bloom.c
+../../../src/crc64.h
+../../../src/crc64.c
+../../../src/murmurhash2.h
+../../../src/murmurhash2.c
+../../../src/obidmscolumn.h
+../../../src/obidmscolumn.c
+../../../src/obitypes.h
+../../../src/obitypes.c
+../../../src/obidmscolumndir.h
+../../../src/obidmscolumndir.c
+../../../src/obiblob_indexer.h
+../../../src/obiblob_indexer.c
+../../../src/obiview.h
+../../../src/obiview.c
+../../../src/hashtable.h
+../../../src/hashtable.c
+../../../src/linked_list.h
+../../../src/linked_list.c
+../../../src/obidmscolumn_array.h
+../../../src/obidmscolumn_array.c
+../../../src/obidmscolumn_blob.h
+../../../src/obidmscolumn_blob.c
+../../../src/obidmscolumn_idx.h
+../../../src/obidmscolumn_idx.c
+../../../src/obidmscolumn_bool.h
+../../../src/obidmscolumn_bool.c
+../../../src/obidmscolumn_char.h
+../../../src/obidmscolumn_char.c
+../../../src/obidmscolumn_float.h
+../../../src/obidmscolumn_float.c
+../../../src/obidmscolumn_int.h
+../../../src/obidmscolumn_int.c
+../../../src/obidmscolumn_qual.h
+../../../src/obidmscolumn_qual.c
+../../../src/obidmscolumn_seq.h
+../../../src/obidmscolumn_seq.c
+../../../src/obidmscolumn_str.h
+../../../src/obidmscolumn_str.c
+../../../src/array_indexer.h
+../../../src/array_indexer.c
+../../../src/char_str_indexer.h
+../../../src/char_str_indexer.c
+../../../src/dna_seq_indexer.h
+../../../src/dna_seq_indexer.c
+../../../src/encode.c
+../../../src/encode.h
+../../../src/uint8_indexer.c
+../../../src/uint8_indexer.h
+../../../src/build_reference_db.c
+../../../src/build_reference_db.h
+../../../src/kmer_similarity.c
+../../../src/kmer_similarity.h
+../../../src/obi_clean.c
+../../../src/obi_clean.h
+../../../src/obi_ecopcr.c
+../../../src/obi_ecopcr.h
+../../../src/obi_ecotag.c
+../../../src/obi_ecotag.h
+../../../src/obidms_taxonomy.c
+../../../src/obidms_taxonomy.h
+../../../src/obilittlebigman.c
+../../../src/obilittlebigman.h
+../../../src/_sse.h
+../../../src/obidebug.h
+../../../src/libecoPCR/libapat/CODES/dft_code.h
+../../../src/libecoPCR/libapat/CODES/dna_code.h
+../../../src/libecoPCR/libapat/CODES/prot_code.h
+../../../src/libecoPCR/libapat/apat_parse.c
+../../../src/libecoPCR/libapat/apat_search.c
+../../../src/libecoPCR/libapat/apat.h
+../../../src/libecoPCR/libapat/Gmach.h
+../../../src/libecoPCR/libapat/Gtypes.h
+../../../src/libecoPCR/libapat/libstki.c
+../../../src/libecoPCR/libapat/libstki.h
+../../../src/libecoPCR/libthermo/nnparams.h
+../../../src/libecoPCR/libthermo/nnparams.c
+../../../src/libecoPCR/ecoapat.c
+../../../src/libecoPCR/ecodna.c
+../../../src/libecoPCR/ecoError.c
+../../../src/libecoPCR/ecoMalloc.c
+../../../src/libecoPCR/ecoPCR.h

python/obitools3/commands/align.pxd

@@ -0,0 +1,18 @@
+#cython: language_level=3
+
+
+cpdef align_columns(bytes dms_n, 
+                    bytes input_view_1_n, 
+                    bytes output_view_n,
+                    bytes input_view_2_n=*,
+                    bytes input_column_1_n=*, 
+                    bytes input_column_2_n=*,
+                    bytes input_elt_1_n=*, 
+                    bytes input_elt_2_n=*,
+                    bytes id_column_1_n=*, 
+                    bytes id_column_2_n=*,
+                    double threshold=*, bint normalize=*, 
+                    int reference=*, bint similarity_mode=*,
+                    bint print_seq=*, bint print_count=*,
+                    bytes comments=*,
+                    int thread_count=*)

python/obitools3/commands/align.pyx

@@ -0,0 +1,274 @@
+#cython: language_level=3
+
+from obitools3.apps.progress cimport ProgressBar  # @UnresolvedImport
+from obitools3.dms import DMS
+from obitools3.dms.view.view cimport View
+from obitools3.uri.decode import open_uri
+from obitools3.apps.optiongroups import addMinimalInputOption, addMinimalOutputOption
+from obitools3.dms.view import RollbackException
+from obitools3.apps.config import logger
+from obitools3.utils cimport tobytes, str2bytes
+
+from obitools3.dms.capi.obilcsalign cimport obi_lcs_align_one_column, \
+                                            obi_lcs_align_two_columns
+
+import time
+import sys
+
+
+__title__="Aligns one sequence column with itself or two sequence columns"
+
+
+def addOptions(parser):
+   
+   addMinimalInputOption(parser)
+   addMinimalOutputOption(parser)
+
+   group=parser.add_argument_group('obi align specific options')
+
+   group.add_argument('--input-2', '-I',
+                      action="store", dest="align:inputuri2",
+                      metavar='<INPUT URI>',
+                      default="",
+                      type=str,
+                      help="Eventually, the URI of the second input to align with the first one.")
+      
+   group.add_argument('--threshold','-t',
+                      action="store", dest="align:threshold",
+                      metavar='<THRESHOLD>',
+                      default=0.0,
+                      type=float,
+                      help="Score threshold. If the score is normalized and expressed in similarity (default),"
+                           " it is an identity, e.g. 0.95 for an identity of 95%%. If the score is normalized"
+                           " and expressed in distance, it is (1.0 - identity), e.g. 0.05 for an identity of 95%%."
+                           " If the score is not normalized and expressed in similarity, it is the length of the"
+                           " Longest Common Subsequence. If the score is not normalized and expressed in distance,"
+                           " it is (reference length - LCS length)."
+                           " Only sequence pairs with a similarity above <THRESHOLD> are printed. Default: 0.00"
+                           " (no threshold).")
+   
+   group.add_argument('--longest-length','-L',
+                      action="store_const", dest="align:reflength",
+                      default=0,
+                      const=1,
+                      help="The reference length is the length of the longest sequence."
+                           " Default: the reference length is the length of the alignment.")
+   
+   group.add_argument('--shortest-length','-l',
+                      action="store_const", dest="align:reflength",
+                      default=0,
+                      const=2,
+                      help="The reference length is the length of the shortest sequence."
+                           " Default: the reference length is the length of the alignment.")
+   
+   group.add_argument('--raw','-r',
+                      action="store_false", dest="align:normalize",
+                      default=True,
+                      help="Raw score, not normalized. Default: score is normalized with the reference sequence length.")
+   
+   group.add_argument('--distance','-D',
+                      action="store_false", dest="align:similarity",
+                      default=True,
+                      help="Score is expressed in distance. Default: score is expressed in similarity.")
+   
+   group.add_argument('--print-seq','-s',
+                      action="store_true", dest="align:printseq",
+                      default=False,
+                      help="The nucleotide sequences are written in the output view. Default: they are not written.")
+   
+   group.add_argument('--print-count','-n',
+                      action="store_true", dest="align:printcount",
+                      default=False,
+                      help="Sequence counts are written in the output view. Default: they are not written.")
+   
+   group.add_argument('--thread-count','-p',   # TODO should probably be in a specific option group
+                      action="store", dest="align:threadcount",
+                      metavar='<THREAD COUNT>',
+                      default=1,
+                      type=int,
+                      help="Number of threads to use for the computation. Default: one.")
+
+
+cpdef align_columns(bytes dms_n, 
+                    bytes input_view_1_n, 
+                    bytes output_view_n,
+                    bytes input_view_2_n=b"",
+                    bytes input_column_1_n=b"", 
+                    bytes input_column_2_n=b"",
+                    bytes input_elt_1_n=b"", 
+                    bytes input_elt_2_n=b"",
+                    bytes id_column_1_n=b"", 
+                    bytes id_column_2_n=b"",
+                    double threshold=0.0, bint normalize=True, 
+                    int reference=0, bint similarity_mode=True,
+                    bint print_seq=False, bint print_count=False,
+                    bytes comments=b"{}",
+                    int thread_count=1) : 
+
+    if input_view_2_n == b"" and input_column_2_n == b"" :
+        if obi_lcs_align_one_column(dms_n, \
+                                    input_view_1_n, \
+                                    input_column_1_n, \
+                                    input_elt_1_n, \
+                                    id_column_1_n, \
+                                    output_view_n, \
+                                    comments, \
+                                    print_seq, \
+                                    print_count, \
+                                    threshold, normalize, reference, similarity_mode,
+                                    thread_count) < 0 :
+            raise Exception("Error aligning sequences")        
+            
+    else:
+        if obi_lcs_align_two_columns(dms_n, \
+                                     input_view_1_n, \
+                                     input_view_2_n, \
+                                     input_column_1_n, \
+                                     input_column_2_n, \
+                                     input_elt_1_n, \
+                                     input_elt_2_n, \
+                                     id_column_1_n, \
+                                     id_column_2_n, \
+                                     output_view_n, \
+                                     comments, \
+                                     print_seq, \
+                                     print_count, \
+                                     threshold, normalize, reference, similarity_mode) < 0 :
+            raise Exception("Error aligning sequences")        
+ 
+ 
+def run(config):
+    
+    DMS.obi_atexit()
+    
+    logger("info", "obi align")
+
+    # Open the input: only the DMS
+    input = open_uri(config['obi']['inputURI'],
+                     dms_only=True)
+    if input is None:
+        raise Exception("Could not read input")
+    i_dms = input[0]
+    i_dms_name = input[0].name
+    i_uri = input[1]
+    i_view_name = i_uri.split(b"/")[0]
+    i_column_name = b""
+    i_element_name = b""
+    if len(i_uri.split(b"/")) == 2:
+        i_column_name = i_uri.split(b"/")[1]
+    if len(i_uri.split(b"/")) == 3:
+        i_element_name = i_uri.split(b"/")[2]
+    if len(i_uri.split(b"/")) > 3:
+        raise Exception("Input URI contains too many elements:", config['obi']['inputURI'])
+
+    # Open the second input if there is one
+    i_dms_2 = None
+    i_dms_name_2 = b""
+    original_i_view_name_2 = b""
+    i_view_name_2 = b""
+    i_column_name_2 = b""
+    i_element_name_2 = b""
+    if config['align']['inputuri2']:
+        input_2 = open_uri(config['align']['inputuri2'],
+                           dms_only=True)
+        if input_2 is None:
+            raise Exception("Could not read second input")
+        i_dms_2 = input_2[0]
+        i_dms_name_2 = i_dms_2.name
+        i_uri_2 = input_2[1]
+        original_i_view_name_2 = i_uri_2.split(b"/")[0]
+        if len(i_uri_2.split(b"/")) == 2:
+            i_column_name_2 = i_uri_2.split(b"/")[1]
+        if len(i_uri_2.split(b"/")) == 3:
+            i_element_name_2 = i_uri_2.split(b"/")[2]
+        if len(i_uri_2.split(b"/")) > 3:
+            raise Exception("Input URI contains too many elements:", config['align']['inputuri2'])
+
+        # If the 2 input DMS are not the same, temporarily import 2nd input view in first input DMS
+        if i_dms != i_dms_2:
+            temp_i_view_name_2 = original_i_view_name_2
+            i=0
+            while temp_i_view_name_2 in i_dms:  # Making sure view name is unique in input DMS
+                temp_i_view_name_2 = original_i_view_name_2+b"_"+str2bytes(str(i))
+                i+=1
+            i_view_name_2 = temp_i_view_name_2
+            View.import_view(i_dms_2.full_path[:-7], i_dms.full_path[:-7], original_i_view_name_2, i_view_name_2)
+
+    # Open the output: only the DMS
+    output = open_uri(config['obi']['outputURI'],
+                      input=False,
+                      dms_only=True)
+    if output is None:
+        raise Exception("Could not create output")
+    o_dms = output[0]
+    o_dms_name = o_dms.name 
+    final_o_view_name = output[1]
+
+    # If the input and output DMS are not the same, align creating a temporary view in the input dms that will be exported to 
+    # the right DMS and deleted in the other afterwards.
+    if i_dms != o_dms:
+        temporary_view_name = final_o_view_name
+        i=0
+        while temporary_view_name in i_dms:  # Making sure view name is unique in input DMS
+            temporary_view_name = final_o_view_name+b"_"+str2bytes(str(i))
+            i+=1
+        o_view_name = temporary_view_name
+    else:
+        o_view_name = final_o_view_name
+        
+    # Save command config in View comments
+    command_line = " ".join(sys.argv[1:])
+    
+    i_dms_list = [i_dms_name]
+    if i_dms_name_2:
+        i_dms_list.append(i_dms_name_2)
+    i_view_list = [i_view_name]
+    if original_i_view_name_2:
+        i_view_list.append(original_i_view_name_2)
+    comments = View.print_config(config, "align", command_line, input_dms_name=i_dms_list, input_view_name=i_view_list)
+    
+    # Call cython alignment function
+      # Using default ID columns of the view. TODO discuss adding option
+    align_columns(i_dms_name,  \
+                  i_view_name,  \
+                  o_view_name,  \
+                  input_view_2_n   = i_view_name_2,  \
+                  input_column_1_n = i_column_name,  \
+                  input_column_2_n = i_column_name_2, \
+                  input_elt_1_n    = i_element_name,  \
+                  input_elt_2_n    = i_element_name_2, \
+                  id_column_1_n    = b"",  \
+                  id_column_2_n    = b"", \
+                  threshold        = config['align']['threshold'], \
+                  normalize        = config['align']['normalize'],  \
+                  reference        = config['align']['reflength'],  \
+                  similarity_mode  = config['align']['similarity'],  \
+                  print_seq        = config['align']['printseq'],  \
+                  print_count      = config['align']['printcount'], \
+                  comments         = comments, \
+                  thread_count     = config['align']['threadcount'])
+
+    # If the input and output DMS are not the same, export result view to output DMS
+    if i_dms != o_dms:
+        View.import_view(i_dms.full_path[:-7], o_dms.full_path[:-7], o_view_name, final_o_view_name)
+
+    # Save command config in output DMS comments
+    o_dms.record_command_line(command_line)
+
+    #print("\n\nOutput view:\n````````````", file=sys.stderr)
+    #print(repr(o_dms[final_o_view_name]), file=sys.stderr)
+
+    # If the two input DMS are different, delete the temporary input view in the first input DMS
+    if i_dms_2 and i_dms != i_dms_2:
+        View.delete_view(i_dms, i_view_name_2)
+        i_dms_2.close()
+
+    # If the input and the output DMS are different, delete the temporary result view in the input DMS
+    if i_dms != o_dms:
+        View.delete_view(i_dms, o_view_name)
+        o_dms.close()
+    
+    i_dms.close()
+    
+    logger("info", "Done.")
+  

python/obitools3/commands/alignpairedend.cfiles

@@ -0,0 +1,103 @@
+../../../src/obi_lcs.h
+../../../src/obi_lcs.c
+../../../src/obierrno.h
+../../../src/obierrno.c
+../../../src/upperband.h
+../../../src/upperband.c
+../../../src/sse_banded_LCS_alignment.h
+../../../src/sse_banded_LCS_alignment.c
+../../../src/obiblob.h
+../../../src/obiblob.c
+../../../src/utils.h
+../../../src/utils.c
+../../../src/obidms.h
+../../../src/obidms.c
+../../../src/libjson/json_utils.h
+../../../src/libjson/json_utils.c
+../../../src/libjson/cJSON.h
+../../../src/libjson/cJSON.c
+../../../src/obiavl.h
+../../../src/obiavl.c
+../../../src/bloom.h
+../../../src/bloom.c
+../../../src/crc64.h
+../../../src/crc64.c
+../../../src/murmurhash2.h
+../../../src/murmurhash2.c
+../../../src/obidmscolumn.h
+../../../src/obidmscolumn.c
+../../../src/obitypes.h
+../../../src/obitypes.c
+../../../src/obidmscolumndir.h
+../../../src/obidmscolumndir.c
+../../../src/obiblob_indexer.h
+../../../src/obiblob_indexer.c
+../../../src/obiview.h
+../../../src/obiview.c
+../../../src/hashtable.h
+../../../src/hashtable.c
+../../../src/linked_list.h
+../../../src/linked_list.c
+../../../src/obidmscolumn_array.h
+../../../src/obidmscolumn_array.c
+../../../src/obidmscolumn_blob.h
+../../../src/obidmscolumn_blob.c
+../../../src/obidmscolumn_idx.h
+../../../src/obidmscolumn_idx.c
+../../../src/obidmscolumn_bool.h
+../../../src/obidmscolumn_bool.c
+../../../src/obidmscolumn_char.h
+../../../src/obidmscolumn_char.c
+../../../src/obidmscolumn_float.h
+../../../src/obidmscolumn_float.c
+../../../src/obidmscolumn_int.h
+../../../src/obidmscolumn_int.c
+../../../src/obidmscolumn_qual.h
+../../../src/obidmscolumn_qual.c
+../../../src/obidmscolumn_seq.h
+../../../src/obidmscolumn_seq.c
+../../../src/obidmscolumn_str.h
+../../../src/obidmscolumn_str.c
+../../../src/array_indexer.h
+../../../src/array_indexer.c
+../../../src/char_str_indexer.h
+../../../src/char_str_indexer.c
+../../../src/dna_seq_indexer.h
+../../../src/dna_seq_indexer.c
+../../../src/encode.c
+../../../src/encode.h
+../../../src/uint8_indexer.c
+../../../src/uint8_indexer.h
+../../../src/build_reference_db.c
+../../../src/build_reference_db.h
+../../../src/kmer_similarity.c
+../../../src/kmer_similarity.h
+../../../src/obi_clean.c
+../../../src/obi_clean.h
+../../../src/obi_ecopcr.c
+../../../src/obi_ecopcr.h
+../../../src/obi_ecotag.c
+../../../src/obi_ecotag.h
+../../../src/obidms_taxonomy.c
+../../../src/obidms_taxonomy.h
+../../../src/obilittlebigman.c
+../../../src/obilittlebigman.h
+../../../src/_sse.h
+../../../src/obidebug.h
+../../../src/libecoPCR/libapat/CODES/dft_code.h
+../../../src/libecoPCR/libapat/CODES/dna_code.h
+../../../src/libecoPCR/libapat/CODES/prot_code.h
+../../../src/libecoPCR/libapat/apat_parse.c
+../../../src/libecoPCR/libapat/apat_search.c
+../../../src/libecoPCR/libapat/apat.h
+../../../src/libecoPCR/libapat/Gmach.h
+../../../src/libecoPCR/libapat/Gtypes.h
+../../../src/libecoPCR/libapat/libstki.c
+../../../src/libecoPCR/libapat/libstki.h
+../../../src/libecoPCR/libthermo/nnparams.h
+../../../src/libecoPCR/libthermo/nnparams.c
+../../../src/libecoPCR/ecoapat.c
+../../../src/libecoPCR/ecodna.c
+../../../src/libecoPCR/ecoError.c
+../../../src/libecoPCR/ecoMalloc.c
+../../../src/libecoPCR/ecoPCR.h

python/obitools3/commands/alignpairedend.pxd

@@ -0,0 +1,4 @@
+#cython: language_level=3
+
+
+cdef object buildAlignment(object direct, object reverse)

python/obitools3/commands/alignpairedend.pyx

@@ -0,0 +1,249 @@
+#cython: language_level=3
+
+from obitools3.apps.progress cimport ProgressBar  # @UnresolvedImport
+from obitools3.dms import DMS
+from obitools3.dms.view import RollbackException
+from obitools3.dms.view.typed_view.view_NUC_SEQS cimport View_NUC_SEQS
+from obitools3.dms.column.column cimport Column
+from obitools3.dms.capi.obiview cimport QUALITY_COLUMN
+from obitools3.dms.capi.obitypes cimport OBI_QUAL
+from obitools3.apps.optiongroups import addMinimalInputOption, addMinimalOutputOption
+from obitools3.uri.decode import open_uri
+from obitools3.apps.config import logger
+from obitools3.libalign._qsassemble import QSolexaReverseAssemble
+from obitools3.libalign._qsrassemble import QSolexaRightReverseAssemble
+from obitools3.libalign._solexapairend import buildConsensus, buildJoinedSequence
+from obitools3.dms.obiseq cimport Nuc_Seq
+from obitools3.libalign.shifted_ali cimport Kmer_similarity, Ali_shifted
+from obitools3.commands.ngsfilter import REVERSE_SEQ_COLUMN_NAME, REVERSE_QUALITY_COLUMN_NAME
+
+import sys
+import os
+
+
+__title__="Aligns paired-ended reads"
+
+
+
+def addOptions(parser):
+
+    addMinimalInputOption(parser)
+    addMinimalOutputOption(parser)
+ 
+    group = parser.add_argument_group('obi alignpairedend specific options')
+
+    group.add_argument('-R', '--reverse-reads',
+                     action="store", dest="alignpairedend:reverse",
+                     metavar="<URI>",
+                     default=None,
+                     type=str,
+                     help="URI to the reverse reads if they are in a different view than the forward reads")
+
+    group.add_argument('--score-min',
+                     action="store", dest="alignpairedend:smin",
+                     metavar="#.###",
+                     default=None,
+                     type=float,
+                     help="Minimum score for keeping alignments")
+
+    group.add_argument('-A', '--true-ali',
+                       action="store_true", dest="alignpairedend:trueali",
+                       default=False,
+                       help="Performs gap free end alignment of sequences instead of using kmers to compute alignments (slower).")
+
+    group.add_argument('-k', '--kmer-size',
+                       action="store", dest="alignpairedend:kmersize",
+                       metavar="#",
+                       default=3,
+                       type=int,
+                       help="K-mer size for kmer comparisons, between 1 and 4 (not when using -A option; default: 3)")
+
+
+la = QSolexaReverseAssemble()
+ra = QSolexaRightReverseAssemble()
+cdef object buildAlignment(object direct, object reverse):
+    
+    if len(direct)==0 or len(reverse)==0:
+        return None
+    
+    la.seqA = direct
+    la.seqB = reverse
+    
+    ali=la()
+    ali.direction='left'
+
+    ra.seqA = direct
+    ra.seqB = reverse
+
+    rali=ra()
+    rali.direction='right'
+     
+    if ali.score < rali.score:
+        ali = rali
+    
+    return ali
+    
+
+def alignmentIterator(entries, aligner): 
+    
+    if type(entries) == list:
+        two_views = True
+        forward = entries[0]
+        reverse = entries[1]
+        entries_len = len(forward)
+    else:
+        two_views = False
+        entries_len = len(entries)
+    
+    for i in range(entries_len):
+        if two_views:
+            seqF = forward[i]
+            seqR = reverse[i]
+        else:
+            seqF = Nuc_Seq.new_from_stored(entries[i])
+            seqR = Nuc_Seq(seqF.id, seqF[REVERSE_SEQ_COLUMN_NAME], quality=seqF[REVERSE_QUALITY_COLUMN_NAME])
+            seqR.index = i
+        
+        ali = aligner(seqF, seqR)
+        
+        if ali is None:
+            continue
+        
+        yield ali
+
+
+def run(config):
+        
+    DMS.obi_atexit()
+    
+    logger("info", "obi alignpairedend")
+       
+    # Open the input
+    
+    two_views = False
+    forward = None
+    reverse = None
+    input = None
+    
+    input = open_uri(config['obi']['inputURI'])
+    if input is None:
+        raise Exception("Could not open input reads")
+    if input[2] != View_NUC_SEQS:
+        raise NotImplementedError('obi alignpairedend only works on NUC_SEQS views')    
+    
+    if "reverse" in config["alignpairedend"]:
+        
+        two_views = True
+        
+        forward = input[1]        
+        
+        rinput = open_uri(config["alignpairedend"]["reverse"])
+        if rinput is None:
+            raise Exception("Could not open reverse reads")
+        if rinput[2] != View_NUC_SEQS:
+            raise NotImplementedError('obi alignpairedend only works on NUC_SEQS views')
+        
+        reverse = rinput[1]
+    
+        if len(forward) != len(reverse):
+            raise Exception("Error: the number of forward and reverse reads are different")
+        
+        entries = [forward, reverse]
+        input_dms_name = [forward.dms.name, reverse.dms.name]
+        input_view_name = [forward.name, reverse.name]
+    
+    else:
+        entries = input[1]
+        input_dms_name = [entries.dms.name]
+        input_view_name = [entries.name]
+
+    if two_views:
+        entries_len = len(forward)
+    else:
+        entries_len = len(entries)
+    
+    # Open the output
+    output = open_uri(config['obi']['outputURI'],
+                      input=False,
+                      newviewtype=View_NUC_SEQS)
+    if output is None:
+        raise Exception("Could not create output view")
+
+    view = output[1]
+    
+    Column.new_column(view, QUALITY_COLUMN, OBI_QUAL)   #TODO output URI quality option?
+
+    if 'smin' in config['alignpairedend']:
+        smin = config['alignpairedend']['smin']
+    else:
+        smin = 0
+
+    # Initialize the progress bar
+    pb = ProgressBar(entries_len, config, seconde=5)
+    
+    if config['alignpairedend']['trueali']:
+        kmer_ali = False
+        aligner = buildAlignment
+    else :
+        kmer_ali = True
+        if type(entries) == list:
+            forward = entries[0]
+            reverse = entries[1]
+            aligner = Kmer_similarity(forward, view2=reverse, kmer_size=config['alignpairedend']['kmersize'])
+        else:
+            aligner = Kmer_similarity(entries, column2=entries[REVERSE_SEQ_COLUMN_NAME], qual_column2=entries[REVERSE_QUALITY_COLUMN_NAME], kmer_size=config['alignpairedend']['kmersize'])
+        
+    ba = alignmentIterator(entries, aligner)
+
+    i = 0
+    for ali in ba:
+        
+        pb(i)
+        
+        consensus = view[i]
+        
+        if not two_views:
+            seqF = entries[i]
+        else:
+            seqF = forward[i]
+                
+        if smin > 0:
+            if (ali.score > smin) :
+                buildConsensus(ali, consensus, seqF)
+            else:
+                if not two_views:
+                    seqR = Nuc_Seq(seqF.id, seqF[REVERSE_SEQ_COLUMN_NAME], quality = seqF[REVERSE_QUALITY_COLUMN_NAME])
+                else:
+                    seqR = reverse[i]
+                buildJoinedSequence(ali, seqR, consensus, forward=seqF)
+                
+            consensus[b"smin"] = smin
+        else:
+            buildConsensus(ali, consensus, seqF)
+                
+        if kmer_ali :
+            ali.free()
+    
+        i+=1
+
+    pb(i, force=True)
+    print("", file=sys.stderr)
+
+    if kmer_ali :
+        aligner.free()
+
+    # Save command config in View and DMS comments
+    command_line = " ".join(sys.argv[1:])
+    view.write_config(config, "alignpairedend", command_line, input_dms_name=input_dms_name, input_view_name=input_view_name)
+    output[0].record_command_line(command_line)
+
+    #print("\n\nOutput view:\n````````````", file=sys.stderr)
+    #print(repr(view), file=sys.stderr)
+    
+    input[0].close()
+    if two_views:
+        rinput[0].close()
+    output[0].close()
+
+    logger("info", "Done.")
+    

python/obitools3/commands/annotate.cfiles

@@ -0,0 +1,103 @@
+../../../src/obi_lcs.h
+../../../src/obi_lcs.c
+../../../src/obierrno.h
+../../../src/obierrno.c
+../../../src/upperband.h
+../../../src/upperband.c
+../../../src/sse_banded_LCS_alignment.h
+../../../src/sse_banded_LCS_alignment.c
+../../../src/obiblob.h
+../../../src/obiblob.c
+../../../src/utils.h
+../../../src/utils.c
+../../../src/obidms.h
+../../../src/obidms.c
+../../../src/libjson/json_utils.h
+../../../src/libjson/json_utils.c
+../../../src/libjson/cJSON.h
+../../../src/libjson/cJSON.c
+../../../src/obiavl.h
+../../../src/obiavl.c
+../../../src/bloom.h
+../../../src/bloom.c
+../../../src/crc64.h
+../../../src/crc64.c
+../../../src/murmurhash2.h
+../../../src/murmurhash2.c
+../../../src/obidmscolumn.h
+../../../src/obidmscolumn.c
+../../../src/obitypes.h
+../../../src/obitypes.c
+../../../src/obidmscolumndir.h
+../../../src/obidmscolumndir.c
+../../../src/obiblob_indexer.h
+../../../src/obiblob_indexer.c
+../../../src/obiview.h
+../../../src/obiview.c
+../../../src/hashtable.h
+../../../src/hashtable.c
+../../../src/linked_list.h
+../../../src/linked_list.c
+../../../src/obidmscolumn_array.h
+../../../src/obidmscolumn_array.c
+../../../src/obidmscolumn_blob.h
+../../../src/obidmscolumn_blob.c
+../../../src/obidmscolumn_idx.h
+../../../src/obidmscolumn_idx.c
+../../../src/obidmscolumn_bool.h
+../../../src/obidmscolumn_bool.c
+../../../src/obidmscolumn_char.h
+../../../src/obidmscolumn_char.c
+../../../src/obidmscolumn_float.h
+../../../src/obidmscolumn_float.c
+../../../src/obidmscolumn_int.h
+../../../src/obidmscolumn_int.c
+../../../src/obidmscolumn_qual.h
+../../../src/obidmscolumn_qual.c
+../../../src/obidmscolumn_seq.h
+../../../src/obidmscolumn_seq.c
+../../../src/obidmscolumn_str.h
+../../../src/obidmscolumn_str.c
+../../../src/array_indexer.h
+../../../src/array_indexer.c
+../../../src/char_str_indexer.h
+../../../src/char_str_indexer.c
+../../../src/dna_seq_indexer.h
+../../../src/dna_seq_indexer.c
+../../../src/encode.c
+../../../src/encode.h
+../../../src/uint8_indexer.c
+../../../src/uint8_indexer.h
+../../../src/build_reference_db.c
+../../../src/build_reference_db.h
+../../../src/kmer_similarity.c
+../../../src/kmer_similarity.h
+../../../src/obi_clean.c
+../../../src/obi_clean.h
+../../../src/obi_ecopcr.c
+../../../src/obi_ecopcr.h
+../../../src/obi_ecotag.c
+../../../src/obi_ecotag.h
+../../../src/obidms_taxonomy.c
+../../../src/obidms_taxonomy.h
+../../../src/obilittlebigman.c
+../../../src/obilittlebigman.h
+../../../src/_sse.h
+../../../src/obidebug.h
+../../../src/libecoPCR/libapat/CODES/dft_code.h
+../../../src/libecoPCR/libapat/CODES/dna_code.h
+../../../src/libecoPCR/libapat/CODES/prot_code.h
+../../../src/libecoPCR/libapat/apat_parse.c
+../../../src/libecoPCR/libapat/apat_search.c
+../../../src/libecoPCR/libapat/apat.h
+../../../src/libecoPCR/libapat/Gmach.h
+../../../src/libecoPCR/libapat/Gtypes.h
+../../../src/libecoPCR/libapat/libstki.c
+../../../src/libecoPCR/libapat/libstki.h
+../../../src/libecoPCR/libthermo/nnparams.h
+../../../src/libecoPCR/libthermo/nnparams.c
+../../../src/libecoPCR/ecoapat.c
+../../../src/libecoPCR/ecodna.c
+../../../src/libecoPCR/ecoError.c
+../../../src/libecoPCR/ecoMalloc.c
+../../../src/libecoPCR/ecoPCR.h

python/obitools3/commands/annotate.pyx

@@ -0,0 +1,382 @@
+#cython: language_level=3
+
+from obitools3.apps.progress cimport ProgressBar  # @UnresolvedImport
+from obitools3.dms import DMS
+from obitools3.dms.view.view cimport View, Line_selection
+from obitools3.uri.decode import open_uri
+from obitools3.apps.optiongroups import addMinimalInputOption, addTaxonomyOption, addMinimalOutputOption
+from obitools3.dms.view import RollbackException
+from functools import reduce
+from obitools3.apps.config import logger
+from obitools3.utils cimport tobytes, str2bytes
+from obitools3.dms.capi.obiview cimport NUC_SEQUENCE_COLUMN, \
+                                        ID_COLUMN, \
+                                        DEFINITION_COLUMN, \
+                                        QUALITY_COLUMN, \
+                                        COUNT_COLUMN
+
+import time
+import math 
+import sys
+
+ 
+__title__="Annotate views with new tags and edit existing annotations"
+
+
+SPECIAL_COLUMNS = [NUC_SEQUENCE_COLUMN, ID_COLUMN, DEFINITION_COLUMN, QUALITY_COLUMN]
+
+ 
+def addOptions(parser):
+    
+    addMinimalInputOption(parser)
+    addTaxonomyOption(parser)
+    addMinimalOutputOption(parser)
+
+    group=parser.add_argument_group('obi annotate specific options')
+ 
+    group.add_argument('--seq-rank',   # TODO seq/elt/line???
+                       action="store_true", 
+                       dest="annotate:add_rank",
+                       default=False,
+                       help="Add a rank attribute to the sequence "
+                            "indicating the sequence position in the data.")
+ 
+    group.add_argument('-R', '--rename-tag',
+                       action="append", 
+                       dest="annotate:rename_tags",
+                       metavar="<OLD_NAME:NEW_NAME>",
+                       type=str,
+                       default=[],
+                       help="Change tag name from OLD_NAME to NEW_NAME.")
+
+    group.add_argument('-D', '--delete-tag',
+                       action="append", 
+                       dest="annotate:delete_tags",
+                       metavar="<TAG_NAME>",
+                       type=str,
+                       default=[],
+                       help="Delete tag TAG_NAME.")
+
+    group.add_argument('-S', '--set-tag',
+                       action="append", 
+                       dest="annotate:set_tags",
+                       metavar="<TAG_NAME:PYTHON_EXPRESSION>",
+                       type=str,
+                       default=[],
+                       help="Add a new tag named TAG_NAME with "
+                            "a value computed from PYTHON_EXPRESSION.")
+
+    group.add_argument('--set-identifier',
+                       action="store", 
+                       dest="annotate:set_identifier",
+                       metavar="<PYTHON_EXPRESSION>",
+                       type=str,
+                       default=None,
+                       help="Set sequence identifier with "
+                            "a value computed from PYTHON_EXPRESSION.")
+    
+    group.add_argument('--set-sequence',
+                       action="store", 
+                       dest="annotate:set_sequence",
+                       metavar="<PYTHON_EXPRESSION>",
+                       type=str,
+                       default=None,
+                       help="Change the sequence itself with "
+                            "a value computed from PYTHON_EXPRESSION.")
+
+    group.add_argument('--set-definition',
+                       action="store", 
+                       dest="annotate:set_definition",
+                       metavar="<PYTHON_EXPRESSION>",
+                       type=str,
+                       default=None,
+                       help="Set sequence definition with "
+                            "a value computed from PYTHON_EXPRESSION.")
+
+    group.add_argument('--run',
+                       action="store", 
+                       dest="annotate:run",
+                       metavar="<PYTHON_EXPRESSION>",
+                       type=str,
+                       default=None,
+                       help="Run a python expression on each element.")
+
+    group.add_argument('-C', '--clear',
+                       action="store_true", 
+                       dest="annotate:clear",
+                       default=False,
+                       help="Clear all tags except the obligatory ones.")
+    
+    group.add_argument('-k','--keep',
+                       action='append',
+                       dest="annotate:keep",
+                       metavar="<TAG>",
+                       default=[],
+                       type=str,
+                       help="Only keep this tag. (Can be specified several times.)")
+    
+    group.add_argument('--length',
+                       action="store_true", 
+                       dest="annotate:length",
+                       default=False,
+                       help="Add 'seq_length' tag with sequence length.")
+    
+    group.add_argument('--with-taxon-at-rank',
+                       action='append',
+                       dest="annotate:taxon_at_rank",
+                       metavar="<RANK_NAME>",
+                       default=[],
+                       type=str,
+                       help="Add taxonomy annotation at the specified rank level RANK_NAME.")
+
+
+def sequenceTaggerGenerator(config, taxo=None):
+    
+    toSet=None
+    newId=None
+    newDef=None
+    newSeq=None
+    length=None
+    add_rank=None
+    run=None
+    
+    if 'set_tags' in config['annotate']:   # TODO default option problem, to fix
+        toSet = [x.split(':',1) for x in config['annotate']['set_tags'] if len(x.split(':',1))==2]
+    if 'set_identifier' in config['annotate']:
+        newId = config['annotate']['set_identifier']
+    if 'set_definition' in config['annotate']:
+        newDef = config['annotate']['set_definition']
+    if 'set_sequence' in config['annotate']:
+        newSeq = config['annotate']['set_sequence']
+    if 'length' in config['annotate']:
+        length = config['annotate']['length']
+    if 'add_rank' in config["annotate"]:
+        add_rank = config["annotate"]["add_rank"]
+    if 'run' in config['annotate']:
+        run = config['annotate']['run']
+    counter = [0]
+    
+    for i in range(len(toSet)):
+        for j in range(len(toSet[i])):
+            toSet[i][j] = tobytes(toSet[i][j])
+
+    annoteRank=[]
+    if config['annotate']['taxon_at_rank']:
+        if taxo is not None:
+            annoteRank = config['annotate']['taxon_at_rank']
+        else:
+            raise Exception("A taxonomy must be provided to annotate taxon ranks")
+    
+    def sequenceTagger(seq):
+                
+        if counter[0]>=0:
+            counter[0]+=1
+                            
+        for rank in annoteRank:
+            if 'taxid' in seq:
+                taxid = seq['taxid']
+                if taxid is not None:
+                    rtaxid = taxo.get_taxon_at_rank(taxid, rank)
+                    if rtaxid is not None:
+                        scn = taxo.get_scientific_name(rtaxid)
+                    else:
+                        scn=None
+                    seq[rank]=rtaxid
+                    seq["%s_name"%rank]=scn
+             
+        if add_rank:
+            seq['seq_rank']=counter[0]
+    
+        for i,v in toSet:
+            #try:
+            if taxo is not None:
+                environ = {'taxonomy' : taxo, 'sequence':seq, 'counter':counter[0], 'math':math}
+            else:
+                environ = {'sequence':seq, 'counter':counter[0], 'math':math}
+            val = eval(v, environ, seq)
+            #except Exception,e:       # TODO discuss usefulness of this
+            #    if options.onlyValid:
+            #        raise e
+            #    val = v
+            seq[i]=val
+
+        if length:
+            seq['seq_length']=len(seq)
+
+        if newId is not None:
+#            try:
+            if taxo is not None:
+                environ = {'taxonomy' : taxo, 'sequence':seq, 'counter':counter[0], 'math':math}
+            else:
+                environ = {'sequence':seq, 'counter':counter[0], 'math':math}     
+            val = eval(newId, environ, seq)
+#            except Exception,e:
+#                if options.onlyValid:
+#                    raise e
+#                val = newId
+            seq.id=val
+
+        if newDef is not None:
+#            try:
+            if taxo is not None:
+                environ = {'taxonomy' : taxo, 'sequence':seq, 'counter':counter[0], 'math':math}
+            else:
+                environ = {'sequence':seq, 'counter':counter[0], 'math':math}     
+            val = eval(newDef, environ, seq)
+#            except Exception,e:
+#                if options.onlyValid:
+#                    raise e
+#                val = newDef
+            seq.definition=val
+#             
+        if newSeq is not None:
+#            try:
+            if taxo is not None:
+                environ = {'taxonomy' : taxo, 'sequence':seq, 'counter':counter[0], 'math':math}
+            else:
+                environ = {'sequence':seq, 'counter':counter[0], 'math':math}     
+            val = eval(newSeq, environ, seq)
+#            except Exception,e:
+#                if options.onlyValid:
+#                    raise e
+#                val = newSeq
+            seq.seq=val
+            if 'seq_length' in seq:
+                seq['seq_length']=len(seq)
+            # Delete quality since it must match the sequence.
+            # TODO discuss deleting for each sequence separately
+            if QUALITY_COLUMN in seq:
+                seq.view.delete_column(QUALITY_COLUMN)
+                    
+        if run is not None:
+#            try:
+            if taxo is not None:
+                environ = {'taxonomy' : taxo, 'sequence':seq, 'counter':counter[0], 'math':math}
+            else:
+                environ = {'sequence':seq, 'counter':counter[0], 'math':math}     
+            eval(run, environ, seq)
+#            except Exception,e:
+#                if options.onlyValid:
+#                    raise e
+
+    return sequenceTagger
+
+
+def run(config):
+     
+    DMS.obi_atexit()
+    
+    logger("info", "obi annotate")
+
+    # Open the input
+    input = open_uri(config['obi']['inputURI'])
+    if input is None:
+        raise Exception("Could not read input view")
+    i_dms = input[0]
+    i_view = input[1]
+    i_view_name = input[1].name
+
+    # Open the output: only the DMS, as the output view is going to be created by cloning the input view
+    # (could eventually be done via an open_uri() argument)
+    output = open_uri(config['obi']['outputURI'],
+                      input=False,
+                      dms_only=True)
+    if output is None:
+        raise Exception("Could not create output view")
+    o_dms = output[0]
+    o_view_name = output[1]
+    
+    # If the input and output DMS are not the same, import the input view in the output DMS before cloning it to modify it
+    # (could be the other way around: clone and modify in the input DMS then import the new view in the output DMS)
+    if i_dms != o_dms:
+        imported_view_name = i_view_name
+        i=0
+        while imported_view_name in o_dms:  # Making sure view name is unique in output DMS
+            imported_view_name = i_view_name+b"_"+str2bytes(str(i))
+            i+=1
+        View.import_view(i_dms.full_path[:-7], o_dms.full_path[:-7], i_view_name, imported_view_name)
+        i_view = o_dms[imported_view_name]
+        
+    # Clone output view from input view
+    o_view = i_view.clone(o_view_name)
+    if o_view is None:
+        raise Exception("Couldn't create output view")
+    i_view.close()
+
+    # Open taxonomy if there is one
+    if 'taxoURI' in config['obi'] and config['obi']['taxoURI'] is not None:
+        taxo_uri = open_uri(config['obi']['taxoURI'])
+        if taxo_uri is None:
+            raise Exception("Couldn't open taxonomy")
+        taxo = taxo_uri[1]
+    else :
+        taxo = None
+
+    # Initialize the progress bar
+    pb = ProgressBar(len(o_view), config, seconde=5)
+
+    try:
+
+        # Apply editions
+        # Editions at view level
+        if 'delete_tags' in config['annotate']:
+            toDelete = config['annotate']['delete_tags'][:]
+        if 'rename_tags' in config['annotate']:
+            toRename = [x.split(':',1) for x in config['annotate']['rename_tags'] if len(x.split(':',1))==2]
+        if 'clear' in config['annotate']:
+            clear = config['annotate']['clear']
+        if 'keep' in config['annotate']:
+            keep = config['annotate']['keep']
+        for i in range(len(toDelete)):
+            toDelete[i] = tobytes(toDelete[i])
+        for i in range(len(toRename)):
+            for j in range(len(toRename[i])):
+                toRename[i][j] = tobytes(toRename[i][j])
+        for i in range(len(keep)):
+            keep[i] = tobytes(keep[i])
+        keep = set(keep)
+    
+        if clear or keep:
+            keys = [k for k in o_view.keys()]
+            for k in keys:
+                if k not in keep and k not in SPECIAL_COLUMNS:
+                    o_view.delete_column(k)
+        else:
+            for k in toDelete:
+                o_view.delete_column(k)
+            for old_name, new_name in toRename:
+                if old_name in o_view:
+                    o_view.rename_column(old_name, new_name)
+        
+        # Editions at line level
+        sequenceTagger = sequenceTaggerGenerator(config, taxo=taxo)
+        for i in range(len(o_view)):
+            pb(i)
+            sequenceTagger(o_view[i])
+
+    except Exception, e:
+        raise RollbackException("obi annotate error, rollbacking view: "+str(e), o_view)
+
+    pb(i, force=True)
+    print("", file=sys.stderr)
+    
+    # Save command config in View and DMS comments
+    command_line = " ".join(sys.argv[1:])
+    input_dms_name=[input[0].name]
+    input_view_name=[i_view_name]
+    if 'taxoURI' in config['obi'] and config['obi']['taxoURI'] is not None:
+        input_dms_name.append(config['obi']['taxoURI'].split("/")[-3])
+        input_view_name.append("taxonomy/"+config['obi']['taxoURI'].split("/")[-1])
+    o_view.write_config(config, "annotate", command_line, input_dms_name=input_dms_name, input_view_name=input_view_name)
+    output[0].record_command_line(command_line)
+
+    #print("\n\nOutput view:\n````````````", file=sys.stderr)
+    #print(repr(o_view), file=sys.stderr)
+
+    # If the input and the output DMS are different, delete the temporary imported view used to create the final view
+    if i_dms != o_dms:
+        View.delete_view(o_dms, imported_view_name)
+        o_dms.close()
+    i_dms.close()
+
+    logger("info", "Done.")

python/obitools3/commands/build_ref_db.cfiles

@@ -0,0 +1,103 @@
+../../../src/obi_lcs.h
+../../../src/obi_lcs.c
+../../../src/obierrno.h
+../../../src/obierrno.c
+../../../src/upperband.h
+../../../src/upperband.c
+../../../src/sse_banded_LCS_alignment.h
+../../../src/sse_banded_LCS_alignment.c
+../../../src/obiblob.h
+../../../src/obiblob.c
+../../../src/utils.h
+../../../src/utils.c
+../../../src/obidms.h
+../../../src/obidms.c
+../../../src/libjson/json_utils.h
+../../../src/libjson/json_utils.c
+../../../src/libjson/cJSON.h
+../../../src/libjson/cJSON.c
+../../../src/obiavl.h
+../../../src/obiavl.c
+../../../src/bloom.h
+../../../src/bloom.c
+../../../src/crc64.h
+../../../src/crc64.c
+../../../src/murmurhash2.h
+../../../src/murmurhash2.c
+../../../src/obidmscolumn.h
+../../../src/obidmscolumn.c
+../../../src/obitypes.h
+../../../src/obitypes.c
+../../../src/obidmscolumndir.h
+../../../src/obidmscolumndir.c
+../../../src/obiblob_indexer.h
+../../../src/obiblob_indexer.c
+../../../src/obiview.h
+../../../src/obiview.c
+../../../src/hashtable.h
+../../../src/hashtable.c
+../../../src/linked_list.h
+../../../src/linked_list.c
+../../../src/obidmscolumn_array.h
+../../../src/obidmscolumn_array.c
+../../../src/obidmscolumn_blob.h
+../../../src/obidmscolumn_blob.c
+../../../src/obidmscolumn_idx.h
+../../../src/obidmscolumn_idx.c
+../../../src/obidmscolumn_bool.h
+../../../src/obidmscolumn_bool.c
+../../../src/obidmscolumn_char.h
+../../../src/obidmscolumn_char.c
+../../../src/obidmscolumn_float.h
+../../../src/obidmscolumn_float.c
+../../../src/obidmscolumn_int.h
+../../../src/obidmscolumn_int.c
+../../../src/obidmscolumn_qual.h
+../../../src/obidmscolumn_qual.c
+../../../src/obidmscolumn_seq.h
+../../../src/obidmscolumn_seq.c
+../../../src/obidmscolumn_str.h
+../../../src/obidmscolumn_str.c
+../../../src/array_indexer.h
+../../../src/array_indexer.c
+../../../src/char_str_indexer.h
+../../../src/char_str_indexer.c
+../../../src/dna_seq_indexer.h
+../../../src/dna_seq_indexer.c
+../../../src/encode.c
+../../../src/encode.h
+../../../src/uint8_indexer.c
+../../../src/uint8_indexer.h
+../../../src/build_reference_db.c
+../../../src/build_reference_db.h
+../../../src/kmer_similarity.c
+../../../src/kmer_similarity.h
+../../../src/obi_clean.c
+../../../src/obi_clean.h
+../../../src/obi_ecopcr.c
+../../../src/obi_ecopcr.h
+../../../src/obi_ecotag.c
+../../../src/obi_ecotag.h
+../../../src/obidms_taxonomy.c
+../../../src/obidms_taxonomy.h
+../../../src/obilittlebigman.c
+../../../src/obilittlebigman.h
+../../../src/_sse.h
+../../../src/obidebug.h
+../../../src/libecoPCR/libapat/CODES/dft_code.h
+../../../src/libecoPCR/libapat/CODES/dna_code.h
+../../../src/libecoPCR/libapat/CODES/prot_code.h
+../../../src/libecoPCR/libapat/apat_parse.c
+../../../src/libecoPCR/libapat/apat_search.c
+../../../src/libecoPCR/libapat/apat.h
+../../../src/libecoPCR/libapat/Gmach.h
+../../../src/libecoPCR/libapat/Gtypes.h
+../../../src/libecoPCR/libapat/libstki.c
+../../../src/libecoPCR/libapat/libstki.h
+../../../src/libecoPCR/libthermo/nnparams.h
+../../../src/libecoPCR/libthermo/nnparams.c
+../../../src/libecoPCR/ecoapat.c
+../../../src/libecoPCR/ecodna.c
+../../../src/libecoPCR/ecoError.c
+../../../src/libecoPCR/ecoMalloc.c
+../../../src/libecoPCR/ecoPCR.h

python/obitools3/commands/build_ref_db.pyx

@@ -0,0 +1,105 @@
+#cython: language_level=3
+
+from obitools3.apps.progress cimport ProgressBar  # @UnresolvedImport
+from obitools3.dms.dms cimport DMS
+from obitools3.dms.view import RollbackException
+from obitools3.dms.capi.build_reference_db cimport build_reference_db
+from obitools3.apps.optiongroups import addMinimalInputOption, addTaxonomyOption, addMinimalOutputOption
+from obitools3.uri.decode import open_uri
+from obitools3.apps.config import logger
+from obitools3.utils cimport tobytes, str2bytes
+from obitools3.dms.view.view cimport View
+from obitools3.dms.view.typed_view.view_NUC_SEQS cimport View_NUC_SEQS
+
+import sys
+
+
+__title__="Tag a set of sequences for PCR and sequencing errors identification"
+
+
+def addOptions(parser):
+
+    addMinimalInputOption(parser)
+    addTaxonomyOption(parser)
+    addMinimalOutputOption(parser)
+ 
+    group = parser.add_argument_group('obi build_ref_db specific options')
+
+    group.add_argument('--threshold','-t',
+                      action="store", dest="build_ref_db:threshold",
+                      metavar='<THRESHOLD>',
+                      default=0.0,
+                      type=float,
+                      help="Score threshold as a normalized identity, e.g. 0.95 for an identity of 95%%. Default: 0.00"
+                           " (no threshold).")
+
+
+def run(config):
+        
+    DMS.obi_atexit()
+    
+    logger("info", "obi build_ref_db")
+
+    # Open the input: only the DMS
+    input = open_uri(config['obi']['inputURI'],
+                     dms_only=True)
+    if input is None:
+        raise Exception("Could not read input")
+    i_dms = input[0]
+    i_dms_name = input[0].name
+    i_view_name = input[1]
+
+    # Open the output: only the DMS
+    output = open_uri(config['obi']['outputURI'],
+                      input=False,
+                      dms_only=True)
+    if output is None:
+        raise Exception("Could not create output")
+    o_dms = output[0]
+    final_o_view_name = output[1]
+    
+    # If the input and output DMS are not the same, build the database creating a temporary view that will be exported to 
+    # the right DMS and deleted in the other afterwards.
+    if i_dms != o_dms:
+        temporary_view_name = final_o_view_name
+        i=0
+        while temporary_view_name in i_dms:  # Making sure view name is unique in input DMS
+            temporary_view_name = final_o_view_name+b"_"+str2bytes(str(i))
+            i+=1
+        o_view_name = temporary_view_name
+    else:
+        o_view_name = final_o_view_name
+
+    # Read taxonomy name
+    taxonomy_name = config['obi']['taxoURI'].split("/")[-1]   # Robust in theory
+
+    # Save command config in View comments
+    command_line = " ".join(sys.argv[1:])
+    input_dms_name=[i_dms_name]
+    input_view_name= [i_view_name]
+    input_dms_name.append(config['obi']['taxoURI'].split("/")[-3])
+    input_view_name.append("taxonomy/"+config['obi']['taxoURI'].split("/")[-1])
+    comments = View.print_config(config, "build_ref_db", command_line, input_dms_name=input_dms_name, input_view_name=input_view_name)
+
+    if build_reference_db(tobytes(i_dms_name), tobytes(i_view_name), tobytes(taxonomy_name), tobytes(o_view_name), comments, config['build_ref_db']['threshold']) < 0:
+        raise Exception("Error building a reference database")
+    
+    # If the input and output DMS are not the same, export result view to output DMS
+    if i_dms != o_dms:
+        View.import_view(i_dms.full_path[:-7], o_dms.full_path[:-7], o_view_name, final_o_view_name)
+    
+    # Save command config in DMS comments
+    o_dms.record_command_line(command_line)
+
+    #print("\n\nOutput view:\n````````````", file=sys.stderr)
+    #print(repr(o_dms[final_o_view_name]), file=sys.stderr)
+
+    # If the input and the output DMS are different, delete the temporary result view in the input DMS
+    if i_dms != o_dms:
+        View.delete_view(i_dms, o_view_name)
+        o_dms.close()
+    
+    i_dms.close()
+
+    logger("info", "Done.")
+    

python/obitools3/commands/clean.cfiles

@@ -0,0 +1,103 @@
+../../../src/obi_lcs.h
+../../../src/obi_lcs.c
+../../../src/obierrno.h
+../../../src/obierrno.c
+../../../src/upperband.h
+../../../src/upperband.c
+../../../src/sse_banded_LCS_alignment.h
+../../../src/sse_banded_LCS_alignment.c
+../../../src/obiblob.h
+../../../src/obiblob.c
+../../../src/utils.h
+../../../src/utils.c
+../../../src/obidms.h
+../../../src/obidms.c
+../../../src/libjson/json_utils.h
+../../../src/libjson/json_utils.c
+../../../src/libjson/cJSON.h
+../../../src/libjson/cJSON.c
+../../../src/obiavl.h
+../../../src/obiavl.c
+../../../src/bloom.h
+../../../src/bloom.c
+../../../src/crc64.h
+../../../src/crc64.c
+../../../src/murmurhash2.h
+../../../src/murmurhash2.c
+../../../src/obidmscolumn.h
+../../../src/obidmscolumn.c
+../../../src/obitypes.h
+../../../src/obitypes.c
+../../../src/obidmscolumndir.h
+../../../src/obidmscolumndir.c
+../../../src/obiblob_indexer.h
+../../../src/obiblob_indexer.c
+../../../src/obiview.h
+../../../src/obiview.c
+../../../src/hashtable.h
+../../../src/hashtable.c
+../../../src/linked_list.h
+../../../src/linked_list.c
+../../../src/obidmscolumn_array.h
+../../../src/obidmscolumn_array.c
+../../../src/obidmscolumn_blob.h
+../../../src/obidmscolumn_blob.c
+../../../src/obidmscolumn_idx.h
+../../../src/obidmscolumn_idx.c
+../../../src/obidmscolumn_bool.h
+../../../src/obidmscolumn_bool.c
+../../../src/obidmscolumn_char.h
+../../../src/obidmscolumn_char.c
+../../../src/obidmscolumn_float.h
+../../../src/obidmscolumn_float.c
+../../../src/obidmscolumn_int.h
+../../../src/obidmscolumn_int.c
+../../../src/obidmscolumn_qual.h
+../../../src/obidmscolumn_qual.c
+../../../src/obidmscolumn_seq.h
+../../../src/obidmscolumn_seq.c
+../../../src/obidmscolumn_str.h
+../../../src/obidmscolumn_str.c
+../../../src/array_indexer.h
+../../../src/array_indexer.c
+../../../src/char_str_indexer.h
+../../../src/char_str_indexer.c
+../../../src/dna_seq_indexer.h
+../../../src/dna_seq_indexer.c
+../../../src/encode.c
+../../../src/encode.h
+../../../src/uint8_indexer.c
+../../../src/uint8_indexer.h
+../../../src/build_reference_db.c
+../../../src/build_reference_db.h
+../../../src/kmer_similarity.c
+../../../src/kmer_similarity.h
+../../../src/obi_clean.c
+../../../src/obi_clean.h
+../../../src/obi_ecopcr.c
+../../../src/obi_ecopcr.h
+../../../src/obi_ecotag.c
+../../../src/obi_ecotag.h
+../../../src/obidms_taxonomy.c
+../../../src/obidms_taxonomy.h
+../../../src/obilittlebigman.c
+../../../src/obilittlebigman.h
+../../../src/_sse.h
+../../../src/obidebug.h
+../../../src/libecoPCR/libapat/CODES/dft_code.h
+../../../src/libecoPCR/libapat/CODES/dna_code.h
+../../../src/libecoPCR/libapat/CODES/prot_code.h
+../../../src/libecoPCR/libapat/apat_parse.c
+../../../src/libecoPCR/libapat/apat_search.c
+../../../src/libecoPCR/libapat/apat.h
+../../../src/libecoPCR/libapat/Gmach.h
+../../../src/libecoPCR/libapat/Gtypes.h
+../../../src/libecoPCR/libapat/libstki.c
+../../../src/libecoPCR/libapat/libstki.h
+../../../src/libecoPCR/libthermo/nnparams.h
+../../../src/libecoPCR/libthermo/nnparams.c
+../../../src/libecoPCR/ecoapat.c
+../../../src/libecoPCR/ecodna.c
+../../../src/libecoPCR/ecoError.c
+../../../src/libecoPCR/ecoMalloc.c
+../../../src/libecoPCR/ecoPCR.h

python/obitools3/commands/clean.pyx

@@ -0,0 +1,124 @@
+#cython: language_level=3
+
+from obitools3.apps.progress cimport ProgressBar  # @UnresolvedImport
+from obitools3.dms.dms cimport DMS
+from obitools3.dms.view import RollbackException
+from obitools3.dms.capi.obiclean cimport obi_clean
+from obitools3.apps.optiongroups import addMinimalInputOption, addMinimalOutputOption
+from obitools3.uri.decode import open_uri
+from obitools3.apps.config import logger
+from obitools3.utils cimport tobytes, str2bytes
+from obitools3.dms.view.view cimport View
+from obitools3.dms.view.typed_view.view_NUC_SEQS cimport View_NUC_SEQS
+
+import sys
+
+
+__title__="Tag a set of sequences for PCR and sequencing errors identification"
+
+
+def addOptions(parser):
+
+    addMinimalInputOption(parser)
+    addMinimalOutputOption(parser)
+ 
+    group = parser.add_argument_group('obi clean specific options')
+
+    group.add_argument('--distance', '-d',
+                       action="store", dest="clean:distance",
+                       metavar='<DISTANCE>',
+                       default=1.0,
+                       type=float,
+                       help="Maximum numbers of errors between two variant sequences. Default: 1.")
+
+    group.add_argument('--sample-tag', '-s',
+                       action="store", 
+                       dest="clean:sample-tag-name",
+                       metavar="<SAMPLE TAG NAME>",
+                       type=str,
+                       default="merged_sample",
+                       help="Name of the tag where sample counts are kept.")
+    
+    group.add_argument('--ratio', '-r',
+                       action="store", dest="clean:ratio",
+                       metavar='<RATIO>',
+                       default=0.5,
+                       type=float,
+                       help="Maximum ratio between the counts of two sequences so that the less abundant one can be considered"
+                            " a variant of the more abundant one. Default: 0.5.")
+ 
+    group.add_argument('--heads-only', '-H',
+                       action="store_true", 
+                       dest="clean:heads-only",
+                       default=False,
+                       help="Only sequences labeled as heads are kept in the output. Default: False")
+
+    group.add_argument('--cluster-tags', '-C',
+                       action="store_true", 
+                       dest="clean:cluster-tags",
+                       default=False,
+                       help="Adds tags for each sequence giving its cluster's head and weight for each sample.")
+
+
+def run(config):
+        
+    DMS.obi_atexit()
+    
+    logger("info", "obi clean")
+
+    # Open the input: only the DMS
+    input = open_uri(config['obi']['inputURI'],
+                     dms_only=True)
+    if input is None:
+        raise Exception("Could not read input")
+    i_dms = input[0]
+    i_dms_name = input[0].name
+    i_view_name = input[1]
+
+    # Open the output: only the DMS
+    output = open_uri(config['obi']['outputURI'],
+                      input=False,
+                      dms_only=True)
+    if output is None:
+        raise Exception("Could not create output")
+    o_dms = output[0]
+    final_o_view_name = output[1]
+    
+    # If the input and output DMS are not the same, run obiclean creating a temporary view that will be exported to 
+    # the right DMS and deleted in the other afterwards.
+    if i_dms != o_dms:
+        temporary_view_name = final_o_view_name
+        i=0
+        while temporary_view_name in i_dms:  # Making sure view name is unique in input DMS
+            temporary_view_name = final_o_view_name+b"_"+str2bytes(str(i))
+            i+=1
+        o_view_name = temporary_view_name
+    else:
+        o_view_name = final_o_view_name
+        
+    # Save command config in View comments
+    command_line = " ".join(sys.argv[1:])
+    comments = View.print_config(config, "clean", command_line, input_dms_name=[i_dms_name], input_view_name=[i_view_name])
+
+    if obi_clean(tobytes(i_dms_name), tobytes(i_view_name), tobytes(config['clean']['sample-tag-name']), tobytes(o_view_name), comments, \
+              config['clean']['distance'], config['clean']['ratio'], config['clean']['heads-only'], 1) < 0:
+        raise Exception("Error running obiclean")
+    
+    # If the input and output DMS are not the same, export result view to output DMS
+    if i_dms != o_dms:
+        View.import_view(i_dms.full_path[:-7], o_dms.full_path[:-7], o_view_name, final_o_view_name)
+    
+    # Save command config in DMS comments
+    o_dms.record_command_line(command_line)
+
+    #print("\n\nOutput view:\n````````````", file=sys.stderr)
+    #print(repr(o_dms[final_o_view_name]), file=sys.stderr)
+
+    # If the input and the output DMS are different, delete the temporary result view in the input DMS
+    if i_dms != o_dms:
+        View.delete_view(i_dms, o_view_name)
+        o_dms.close()
+    
+    i_dms.close()
+
+    logger("info", "Done.")

python/obitools3/commands/count.cfiles

@@ -0,0 +1,103 @@
+../../../src/obi_lcs.h
+../../../src/obi_lcs.c
+../../../src/obierrno.h
+../../../src/obierrno.c
+../../../src/upperband.h
+../../../src/upperband.c
+../../../src/sse_banded_LCS_alignment.h
+../../../src/sse_banded_LCS_alignment.c
+../../../src/obiblob.h
+../../../src/obiblob.c
+../../../src/utils.h
+../../../src/utils.c
+../../../src/obidms.h
+../../../src/obidms.c
+../../../src/libjson/json_utils.h
+../../../src/libjson/json_utils.c
+../../../src/libjson/cJSON.h
+../../../src/libjson/cJSON.c
+../../../src/obiavl.h
+../../../src/obiavl.c
+../../../src/bloom.h
+../../../src/bloom.c
+../../../src/crc64.h
+../../../src/crc64.c
+../../../src/murmurhash2.h
+../../../src/murmurhash2.c
+../../../src/obidmscolumn.h
+../../../src/obidmscolumn.c
+../../../src/obitypes.h
+../../../src/obitypes.c
+../../../src/obidmscolumndir.h
+../../../src/obidmscolumndir.c
+../../../src/obiblob_indexer.h
+../../../src/obiblob_indexer.c
+../../../src/obiview.h
+../../../src/obiview.c
+../../../src/hashtable.h
+../../../src/hashtable.c
+../../../src/linked_list.h
+../../../src/linked_list.c
+../../../src/obidmscolumn_array.h
+../../../src/obidmscolumn_array.c
+../../../src/obidmscolumn_blob.h
+../../../src/obidmscolumn_blob.c
+../../../src/obidmscolumn_idx.h
+../../../src/obidmscolumn_idx.c
+../../../src/obidmscolumn_bool.h
+../../../src/obidmscolumn_bool.c
+../../../src/obidmscolumn_char.h
+../../../src/obidmscolumn_char.c
+../../../src/obidmscolumn_float.h
+../../../src/obidmscolumn_float.c
+../../../src/obidmscolumn_int.h
+../../../src/obidmscolumn_int.c
+../../../src/obidmscolumn_qual.h
+../../../src/obidmscolumn_qual.c
+../../../src/obidmscolumn_seq.h
+../../../src/obidmscolumn_seq.c
+../../../src/obidmscolumn_str.h
+../../../src/obidmscolumn_str.c
+../../../src/array_indexer.h
+../../../src/array_indexer.c
+../../../src/char_str_indexer.h
+../../../src/char_str_indexer.c
+../../../src/dna_seq_indexer.h
+../../../src/dna_seq_indexer.c
+../../../src/encode.c
+../../../src/encode.h
+../../../src/uint8_indexer.c
+../../../src/uint8_indexer.h
+../../../src/build_reference_db.c
+../../../src/build_reference_db.h
+../../../src/kmer_similarity.c
+../../../src/kmer_similarity.h
+../../../src/obi_clean.c
+../../../src/obi_clean.h
+../../../src/obi_ecopcr.c
+../../../src/obi_ecopcr.h
+../../../src/obi_ecotag.c
+../../../src/obi_ecotag.h
+../../../src/obidms_taxonomy.c
+../../../src/obidms_taxonomy.h
+../../../src/obilittlebigman.c
+../../../src/obilittlebigman.h
+../../../src/_sse.h
+../../../src/obidebug.h
+../../../src/libecoPCR/libapat/CODES/dft_code.h
+../../../src/libecoPCR/libapat/CODES/dna_code.h
+../../../src/libecoPCR/libapat/CODES/prot_code.h
+../../../src/libecoPCR/libapat/apat_parse.c
+../../../src/libecoPCR/libapat/apat_search.c
+../../../src/libecoPCR/libapat/apat.h
+../../../src/libecoPCR/libapat/Gmach.h
+../../../src/libecoPCR/libapat/Gtypes.h
+../../../src/libecoPCR/libapat/libstki.c
+../../../src/libecoPCR/libapat/libstki.h
+../../../src/libecoPCR/libthermo/nnparams.h
+../../../src/libecoPCR/libthermo/nnparams.c
+../../../src/libecoPCR/ecoapat.c
+../../../src/libecoPCR/ecodna.c
+../../../src/libecoPCR/ecoError.c
+../../../src/libecoPCR/ecoMalloc.c
+../../../src/libecoPCR/ecoPCR.h

python/obitools3/commands/count.pyx

@@ -0,0 +1,55 @@
+#cython: language_level=3
+
+
+from obitools3.uri.decode import open_uri
+from obitools3.apps.config import logger
+from obitools3.dms import DMS
+from obitools3.apps.optiongroups import addMinimalInputOption
+from obitools3.dms.capi.obiview cimport COUNT_COLUMN
+
+
+__title__="Counts sequence records"
+
+ 
+def addOptions(parser):
+ 
+    addMinimalInputOption(parser)
+ 
+    group = parser.add_argument_group('obi count specific options')
+ 
+    group.add_argument('-s','--sequence',
+                        action="store_true", dest="count:sequence",
+                        default=False,
+                        help="Prints only the number of sequence records.")
+ 
+    group.add_argument('-a','--all',
+                        action="store_true", dest="count:all",
+                        default=False,
+                        help="Prints only the total count of sequence records (if a sequence has no `count` attribute, its default count is 1) (default: False).")
+
+    
+def run(config):
+    
+    DMS.obi_atexit()
+    
+    logger("info", "obi count")
+
+    # Open the input
+    input = open_uri(config['obi']['inputURI'])
+    if input is None:
+        raise Exception("Could not read input")
+    entries = input[1]
+
+    count1 = len(entries)
+    count2 = 0
+    
+    if COUNT_COLUMN in entries and ((config['count']['sequence'] == config['count']['all']) or (config['count']['all'])) :
+        for e in entries:
+            count2+=e[COUNT_COLUMN]
+
+    if COUNT_COLUMN in entries and (config['count']['sequence'] == config['count']['all']):
+        print(count1,count2)
+    elif COUNT_COLUMN in entries and config['count']['all']:
+        print(count2)
+    else:
+        print(count1)

python/obitools3/commands/ecopcr.cfiles

@@ -0,0 +1,103 @@
+../../../src/obi_lcs.h
+../../../src/obi_lcs.c
+../../../src/obierrno.h
+../../../src/obierrno.c
+../../../src/upperband.h
+../../../src/upperband.c
+../../../src/sse_banded_LCS_alignment.h
+../../../src/sse_banded_LCS_alignment.c
+../../../src/obiblob.h
+../../../src/obiblob.c
+../../../src/utils.h
+../../../src/utils.c
+../../../src/obidms.h
+../../../src/obidms.c
+../../../src/libjson/json_utils.h
+../../../src/libjson/json_utils.c
+../../../src/libjson/cJSON.h
+../../../src/libjson/cJSON.c
+../../../src/obiavl.h
+../../../src/obiavl.c
+../../../src/bloom.h
+../../../src/bloom.c
+../../../src/crc64.h
+../../../src/crc64.c
+../../../src/murmurhash2.h
+../../../src/murmurhash2.c
+../../../src/obidmscolumn.h
+../../../src/obidmscolumn.c
+../../../src/obitypes.h
+../../../src/obitypes.c
+../../../src/obidmscolumndir.h
+../../../src/obidmscolumndir.c
+../../../src/obiblob_indexer.h
+../../../src/obiblob_indexer.c
+../../../src/obiview.h
+../../../src/obiview.c
+../../../src/hashtable.h
+../../../src/hashtable.c
+../../../src/linked_list.h
+../../../src/linked_list.c
+../../../src/obidmscolumn_array.h
+../../../src/obidmscolumn_array.c
+../../../src/obidmscolumn_blob.h
+../../../src/obidmscolumn_blob.c
+../../../src/obidmscolumn_idx.h
+../../../src/obidmscolumn_idx.c
+../../../src/obidmscolumn_bool.h
+../../../src/obidmscolumn_bool.c
+../../../src/obidmscolumn_char.h
+../../../src/obidmscolumn_char.c
+../../../src/obidmscolumn_float.h
+../../../src/obidmscolumn_float.c
+../../../src/obidmscolumn_int.h
+../../../src/obidmscolumn_int.c
+../../../src/obidmscolumn_qual.h
+../../../src/obidmscolumn_qual.c
+../../../src/obidmscolumn_seq.h
+../../../src/obidmscolumn_seq.c
+../../../src/obidmscolumn_str.h
+../../../src/obidmscolumn_str.c
+../../../src/array_indexer.h
+../../../src/array_indexer.c
+../../../src/char_str_indexer.h
+../../../src/char_str_indexer.c
+../../../src/dna_seq_indexer.h
+../../../src/dna_seq_indexer.c
+../../../src/encode.c
+../../../src/encode.h
+../../../src/uint8_indexer.c
+../../../src/uint8_indexer.h
+../../../src/build_reference_db.c
+../../../src/build_reference_db.h
+../../../src/kmer_similarity.c
+../../../src/kmer_similarity.h
+../../../src/obi_clean.c
+../../../src/obi_clean.h
+../../../src/obi_ecopcr.c
+../../../src/obi_ecopcr.h
+../../../src/obi_ecotag.c
+../../../src/obi_ecotag.h
+../../../src/obidms_taxonomy.c
+../../../src/obidms_taxonomy.h
+../../../src/obilittlebigman.c
+../../../src/obilittlebigman.h
+../../../src/_sse.h
+../../../src/obidebug.h
+../../../src/libecoPCR/libapat/CODES/dft_code.h
+../../../src/libecoPCR/libapat/CODES/dna_code.h
+../../../src/libecoPCR/libapat/CODES/prot_code.h
+../../../src/libecoPCR/libapat/apat_parse.c
+../../../src/libecoPCR/libapat/apat_search.c
+../../../src/libecoPCR/libapat/apat.h
+../../../src/libecoPCR/libapat/Gmach.h
+../../../src/libecoPCR/libapat/Gtypes.h
+../../../src/libecoPCR/libapat/libstki.c
+../../../src/libecoPCR/libapat/libstki.h
+../../../src/libecoPCR/libthermo/nnparams.h
+../../../src/libecoPCR/libthermo/nnparams.c
+../../../src/libecoPCR/ecoapat.c
+../../../src/libecoPCR/ecodna.c
+../../../src/libecoPCR/ecoError.c
+../../../src/libecoPCR/ecoMalloc.c
+../../../src/libecoPCR/ecoPCR.h

python/obitools3/commands/ecopcr.pyx

@@ -0,0 +1,202 @@
+#cython: language_level=3
+
+from obitools3.apps.progress cimport ProgressBar  # @UnresolvedImport
+from obitools3.dms.dms cimport DMS
+from obitools3.dms.capi.obidms cimport OBIDMS_p
+from obitools3.dms.view import RollbackException
+from obitools3.dms.capi.obiecopcr cimport obi_ecopcr
+from obitools3.apps.optiongroups import addMinimalInputOption, addMinimalOutputOption, addTaxonomyOption
+from obitools3.uri.decode import open_uri
+from obitools3.apps.config import logger
+from obitools3.utils cimport tobytes
+from obitools3.dms.view.typed_view.view_NUC_SEQS cimport View_NUC_SEQS
+from obitools3.dms.view import View
+
+from libc.stdlib  cimport malloc, free
+from libc.stdint  cimport int32_t
+
+import sys
+
+
+__title__="in silico PCR"
+
+
+# TODO: add option to output unique ids
+def addOptions(parser):
+
+    addMinimalInputOption(parser)
+    addTaxonomyOption(parser)
+    addMinimalOutputOption(parser)
+
+ 
+    group = parser.add_argument_group('obi ecopcr specific options')
+
+    group.add_argument('--primer1', '-F',
+                       action="store", dest="ecopcr:primer1",
+                       metavar='<PRIMER>',
+                       type=str,
+                       help="Forward primer.")
+
+    group.add_argument('--primer2', '-R',
+                       action="store", dest="ecopcr:primer2",
+                       metavar='<PRIMER>',
+                       type=str,
+                       help="Reverse primer.")
+
+    group.add_argument('--error', '-e',
+                       action="store", dest="ecopcr:error",
+                       metavar='<ERROR>',
+                       default=0,
+                       type=int,
+                       help="Maximum number of errors (mismatches) allowed per primer. Default: 0.")
+
+    group.add_argument('--min-length', '-l',
+                       action="store", 
+                       dest="ecopcr:min-length",
+                       metavar="<MINIMUM LENGTH>",
+                       type=int,
+                       default=0,
+                       help="Minimum length of the in silico amplified DNA fragment, excluding primers.")
+    
+    group.add_argument('--max-length', '-L',
+                       action="store", 
+                       dest="ecopcr:max-length",
+                       metavar="<MAXIMUM LENGTH>",
+                       type=int,
+                       default=0,
+                       help="Maximum length of the in silico amplified DNA fragment, excluding primers.")
+ 
+    group.add_argument('--restrict-to-taxid', '-r',
+                       action="append", 
+                       dest="ecopcr:restrict-to-taxid",
+                       metavar="<TAXID>",
+                       type=int,
+                       default=[],
+                       help="Only the sequence records corresponding to the taxonomic group identified "
+                            "by TAXID are considered for the in silico PCR. The TAXID is an integer "
+                            "that can be found in the NCBI taxonomic database.")
+ 
+    group.add_argument('--ignore-taxid', '-i',
+                       action="append", 
+                       dest="ecopcr:ignore-taxid",
+                       metavar="<TAXID>",
+                       type=int,
+                       default=[],
+                       help="The sequences of the taxonomic group identified by TAXID are not considered for the in silico PCR.")
+
+    group.add_argument('--circular', '-c',
+                       action="store_true", 
+                       dest="ecopcr:circular",
+                       default=False,
+                       help="Considers that the input sequences are circular (e.g. mitochondrial or chloroplastic DNA).")
+
+    group.add_argument('--salt-concentration', '-a',
+                       action="store", 
+                       dest="ecopcr:salt-concentration",
+                       metavar="<FLOAT>",
+                       type=float,
+                       default=0.05,
+                       help="Salt concentration used for estimating the Tm. Default: 0.05.")
+
+    group.add_argument('--salt-correction-method', '-m',
+                       action="store", 
+                       dest="ecopcr:salt-correction-method",
+                       metavar="<1|2>",
+                       type=int,
+                       default=1,
+                       help="Defines the method used for estimating the Tm (melting temperature) between the primers and their corresponding "
+                            "target sequences. SANTALUCIA: 1, or OWCZARZY: 2. Default: 1.")
+
+    group.add_argument('--keep-nucs', '-D',
+                       action="store", 
+                       dest="ecopcr:keep-nucs",
+                       metavar="<INTEGER>",
+                       type=int,
+                       default=0,
+                       help="Keeps the specified number of nucleotides on each side of the in silico amplified sequences, "
+                            "(already including the amplified DNA fragment plus the two target sequences of the primers).")
+
+    group.add_argument('--kingdom-mode', '-k',
+                       action="store_true", 
+                       dest="ecopcr:kingdom-mode",
+                       default=False,
+                       help="Print in the output the kingdom of the in silico amplified sequences (default: print the superkingdom).")
+
+ 
+
+def run(config):
+
+    cdef int32_t* restrict_to_taxids_p = NULL
+    cdef int32_t* ignore_taxids_p = NULL
+    
+    restrict_to_taxids_len = len(config['ecopcr']['restrict-to-taxid'])
+    restrict_to_taxids_p = <int32_t*> malloc((restrict_to_taxids_len + 1) * sizeof(int32_t))   # +1 for the -1 flagging the end of the array
+    for i in range(restrict_to_taxids_len) :
+        restrict_to_taxids_p[i] = config['ecopcr']['restrict-to-taxid'][i]
+    restrict_to_taxids_p[restrict_to_taxids_len] = -1
+
+    ignore_taxids_len = len(config['ecopcr']['ignore-taxid'])
+    ignore_taxids_p = <int32_t*> malloc((ignore_taxids_len + 1) * sizeof(int32_t))   # +1 for the -1 flagging the end of the array
+    for i in range(ignore_taxids_len) :
+        ignore_taxids_p[i] = config['ecopcr']['ignore-taxid'][i]
+    ignore_taxids_p[ignore_taxids_len] = -1
+    
+    DMS.obi_atexit()
+    
+    logger("info", "obi ecopcr")
+
+    # Open the input: only the DMS
+    input = open_uri(config['obi']['inputURI'],
+                     dms_only=True)
+    if input is None:
+        raise Exception("Could not read input")
+    i_dms = input[0]
+    i_dms_name = input[0].name
+    i_view_name = input[1]
+
+    # Open the output: only the DMS
+    output = open_uri(config['obi']['outputURI'],
+                      input=False,
+                      dms_only=True)
+    if output is None:
+        raise Exception("Could not create output")
+    o_dms = output[0]
+    o_dms_name = output[0].name
+    o_view_name = output[1]
+
+    # Read taxonomy name    
+    taxonomy_name = config['obi']['taxoURI'].split("/")[-1]   # Robust in theory
+    
+    # Save command config in View comments
+    command_line = " ".join(sys.argv[1:])
+    input_dms_name=[i_dms_name]
+    input_view_name= [i_view_name]
+    input_dms_name.append(config['obi']['taxoURI'].split("/")[-3])
+    input_view_name.append("taxonomy/"+config['obi']['taxoURI'].split("/")[-1])
+
+    comments = View.print_config(config, "ecopcr", command_line, input_dms_name=input_dms_name, input_view_name=input_view_name)
+
+    # TODO: primers in comments?
+
+    if obi_ecopcr(tobytes(i_dms_name), tobytes(i_view_name), tobytes(taxonomy_name), \
+                  tobytes(o_dms_name), tobytes(o_view_name), comments, \
+                  tobytes(config['ecopcr']['primer1']), tobytes(config['ecopcr']['primer2']), \
+                  config['ecopcr']['error'], \
+                  config['ecopcr']['min-length'], config['ecopcr']['max-length'], \
+                  restrict_to_taxids_p, ignore_taxids_p, \
+                  config['ecopcr']['circular'], config['ecopcr']['salt-concentration'], config['ecopcr']['salt-correction-method'], \
+                  config['ecopcr']['keep-nucs'], config['ecopcr']['kingdom-mode']) < 0:
+        raise Exception("Error running ecopcr")
+
+    # Save command config in DMS comments
+    o_dms.record_command_line(command_line)
+
+    free(restrict_to_taxids_p)
+    free(ignore_taxids_p)
+    
+    #print("\n\nOutput view:\n````````````", file=sys.stderr)
+    #print(repr(o_dms[o_view_name]), file=sys.stderr)
+
+    o_dms.close()
+
+    logger("info", "Done.")

python/obitools3/commands/ecotag.cfiles

@@ -0,0 +1,103 @@
+../../../src/obi_lcs.h
+../../../src/obi_lcs.c
+../../../src/obierrno.h
+../../../src/obierrno.c
+../../../src/upperband.h
+../../../src/upperband.c
+../../../src/sse_banded_LCS_alignment.h
+../../../src/sse_banded_LCS_alignment.c
+../../../src/obiblob.h
+../../../src/obiblob.c
+../../../src/utils.h
+../../../src/utils.c
+../../../src/obidms.h
+../../../src/obidms.c
+../../../src/libjson/json_utils.h
+../../../src/libjson/json_utils.c
+../../../src/libjson/cJSON.h
+../../../src/libjson/cJSON.c
+../../../src/obiavl.h
+../../../src/obiavl.c
+../../../src/bloom.h
+../../../src/bloom.c
+../../../src/crc64.h
+../../../src/crc64.c
+../../../src/murmurhash2.h
+../../../src/murmurhash2.c
+../../../src/obidmscolumn.h
+../../../src/obidmscolumn.c
+../../../src/obitypes.h
+../../../src/obitypes.c
+../../../src/obidmscolumndir.h
+../../../src/obidmscolumndir.c
+../../../src/obiblob_indexer.h
+../../../src/obiblob_indexer.c
+../../../src/obiview.h
+../../../src/obiview.c
+../../../src/hashtable.h
+../../../src/hashtable.c
+../../../src/linked_list.h
+../../../src/linked_list.c
+../../../src/obidmscolumn_array.h
+../../../src/obidmscolumn_array.c
+../../../src/obidmscolumn_blob.h
+../../../src/obidmscolumn_blob.c
+../../../src/obidmscolumn_idx.h
+../../../src/obidmscolumn_idx.c
+../../../src/obidmscolumn_bool.h
+../../../src/obidmscolumn_bool.c
+../../../src/obidmscolumn_char.h
+../../../src/obidmscolumn_char.c
+../../../src/obidmscolumn_float.h
+../../../src/obidmscolumn_float.c
+../../../src/obidmscolumn_int.h
+../../../src/obidmscolumn_int.c
+../../../src/obidmscolumn_qual.h
+../../../src/obidmscolumn_qual.c
+../../../src/obidmscolumn_seq.h
+../../../src/obidmscolumn_seq.c
+../../../src/obidmscolumn_str.h
+../../../src/obidmscolumn_str.c
+../../../src/array_indexer.h
+../../../src/array_indexer.c
+../../../src/char_str_indexer.h
+../../../src/char_str_indexer.c
+../../../src/dna_seq_indexer.h
+../../../src/dna_seq_indexer.c
+../../../src/encode.c
+../../../src/encode.h
+../../../src/uint8_indexer.c
+../../../src/uint8_indexer.h
+../../../src/build_reference_db.c
+../../../src/build_reference_db.h
+../../../src/kmer_similarity.c
+../../../src/kmer_similarity.h
+../../../src/obi_clean.c
+../../../src/obi_clean.h
+../../../src/obi_ecopcr.c
+../../../src/obi_ecopcr.h
+../../../src/obi_ecotag.c
+../../../src/obi_ecotag.h
+../../../src/obidms_taxonomy.c
+../../../src/obidms_taxonomy.h
+../../../src/obilittlebigman.c
+../../../src/obilittlebigman.h
+../../../src/_sse.h
+../../../src/obidebug.h
+../../../src/libecoPCR/libapat/CODES/dft_code.h
+../../../src/libecoPCR/libapat/CODES/dna_code.h
+../../../src/libecoPCR/libapat/CODES/prot_code.h
+../../../src/libecoPCR/libapat/apat_parse.c
+../../../src/libecoPCR/libapat/apat_search.c
+../../../src/libecoPCR/libapat/apat.h
+../../../src/libecoPCR/libapat/Gmach.h
+../../../src/libecoPCR/libapat/Gtypes.h
+../../../src/libecoPCR/libapat/libstki.c
+../../../src/libecoPCR/libapat/libstki.h
+../../../src/libecoPCR/libthermo/nnparams.h
+../../../src/libecoPCR/libthermo/nnparams.c
+../../../src/libecoPCR/ecoapat.c
+../../../src/libecoPCR/ecodna.c
+../../../src/libecoPCR/ecoError.c
+../../../src/libecoPCR/ecoMalloc.c
+../../../src/libecoPCR/ecoPCR.h

python/obitools3/commands/ecotag.pyx

@@ -0,0 +1,129 @@
+#cython: language_level=3
+
+from obitools3.apps.progress cimport ProgressBar  # @UnresolvedImport
+from obitools3.dms.dms cimport DMS
+from obitools3.dms.view import RollbackException
+from obitools3.dms.capi.obiecotag cimport obi_ecotag
+from obitools3.apps.optiongroups import addMinimalInputOption, addTaxonomyOption, addMinimalOutputOption
+from obitools3.uri.decode import open_uri
+from obitools3.apps.config import logger
+from obitools3.utils cimport tobytes, str2bytes
+from obitools3.dms.view.view cimport View
+from obitools3.dms.view.typed_view.view_NUC_SEQS cimport View_NUC_SEQS
+
+import sys
+
+
+__title__="Taxonomic assignment of sequences"
+
+
+def addOptions(parser):
+
+    addMinimalInputOption(parser)
+    addTaxonomyOption(parser)
+    addMinimalOutputOption(parser)
+ 
+    group = parser.add_argument_group('obi ecotag specific options')
+
+    group.add_argument('--ref-database','-R',
+                      action="store", dest="ecotag:ref_view",
+                      metavar='<REF_VIEW>',
+                      type=str,
+                      help="URI of the view containing the reference database as built by the build_ref_db command.")
+
+    group.add_argument('--minimum-identity','-m',
+                      action="store", dest="ecotag:threshold",
+                      metavar='<THRESHOLD>',
+                      default=0.0,
+                      type=float,
+                      help="Minimum identity to consider for assignment, as a normalized identity, e.g. 0.95 for an identity of 95%%. "
+                           "Default: 0.00 (no threshold).")
+
+def run(config):
+        
+    DMS.obi_atexit()
+    
+    logger("info", "obi ecotag")
+
+    # Open the query view: only the DMS
+    input = open_uri(config['obi']['inputURI'],
+                     dms_only=True)
+    if input is None:
+        raise Exception("Could not read input")
+    i_dms = input[0]
+    i_dms_name = input[0].name
+    i_view_name = input[1]
+
+    # Open the reference view: only the DMS
+    ref = open_uri(config['ecotag']['ref_view'],
+                     dms_only=True)
+    if ref is None:
+        raise Exception("Could not read reference view URI")
+    ref_dms = ref[0]
+    ref_dms_name = ref[0].name
+    ref_view_name = ref[1]
+
+    # Open the output: only the DMS
+    output = open_uri(config['obi']['outputURI'],
+                      input=False,
+                      dms_only=True)
+    if output is None:
+        raise Exception("Could not create output")
+    o_dms = output[0]
+    final_o_view_name = output[1]
+    
+    # If the input and output DMS are not the same, run ecotag creating a temporary view that will be exported to 
+    # the right DMS and deleted in the other afterwards.
+    if i_dms != o_dms:
+        temporary_view_name = final_o_view_name
+        i=0
+        while temporary_view_name in i_dms:  # Making sure view name is unique in input DMS
+            temporary_view_name = final_o_view_name+b"_"+str2bytes(str(i))
+            i+=1
+        o_view_name = temporary_view_name
+    else:
+        o_view_name = final_o_view_name
+
+    # Read taxonomy DMS and name
+    taxo = open_uri(config['obi']['taxoURI'],
+                    dms_only=True)
+    taxo_dms_name = taxo[0].name
+    taxo_dms = taxo[0]
+    taxonomy_name = config['obi']['taxoURI'].split("/")[-1]   # Robust in theory
+
+    # Save command config in View comments
+    command_line = " ".join(sys.argv[1:])
+    input_dms_name=[i_dms_name]
+    input_view_name= [i_view_name]
+    input_dms_name.append(ref_dms_name)
+    input_view_name.append(ref_view_name)
+    input_dms_name.append(config['obi']['taxoURI'].split("/")[-3])
+    input_view_name.append("taxonomy/"+config['obi']['taxoURI'].split("/")[-1])
+    comments = View.print_config(config, "ecotag", command_line, input_dms_name=input_dms_name, input_view_name=input_view_name)
+
+    if obi_ecotag(tobytes(i_dms_name), tobytes(i_view_name), \
+                  tobytes(ref_dms_name), tobytes(ref_view_name), \
+                  tobytes(taxo_dms_name), tobytes(taxonomy_name), \
+                  tobytes(o_view_name), comments, 
+                  config['ecotag']['threshold']) < 0:
+        raise Exception("Error running ecotag")
+    
+    # If the input and output DMS are not the same, export result view to output DMS
+    if i_dms != o_dms:
+        View.import_view(i_dms.full_path[:-7], o_dms.full_path[:-7], o_view_name, final_o_view_name)
+    
+    # Save command config in DMS comments
+    o_dms.record_command_line(command_line)
+
+    #print("\n\nOutput view:\n````````````", file=sys.stderr)
+    #print(repr(o_dms[final_o_view_name]), file=sys.stderr)
+
+    # If the input and the output DMS are different, delete the temporary result view in the input DMS
+    if i_dms != o_dms:
+        View.delete_view(i_dms, o_view_name)
+        o_dms.close()
+    
+    i_dms.close()
+    
+    logger("info", "Done.")
+

python/obitools3/commands/export.cfiles

@@ -0,0 +1,103 @@
+../../../src/obi_lcs.h
+../../../src/obi_lcs.c
+../../../src/obierrno.h
+../../../src/obierrno.c
+../../../src/upperband.h
+../../../src/upperband.c
+../../../src/sse_banded_LCS_alignment.h
+../../../src/sse_banded_LCS_alignment.c
+../../../src/obiblob.h
+../../../src/obiblob.c
+../../../src/utils.h
+../../../src/utils.c
+../../../src/obidms.h
+../../../src/obidms.c
+../../../src/libjson/json_utils.h
+../../../src/libjson/json_utils.c
+../../../src/libjson/cJSON.h
+../../../src/libjson/cJSON.c
+../../../src/obiavl.h
+../../../src/obiavl.c
+../../../src/bloom.h
+../../../src/bloom.c
+../../../src/crc64.h
+../../../src/crc64.c
+../../../src/murmurhash2.h
+../../../src/murmurhash2.c
+../../../src/obidmscolumn.h
+../../../src/obidmscolumn.c
+../../../src/obitypes.h
+../../../src/obitypes.c
+../../../src/obidmscolumndir.h
+../../../src/obidmscolumndir.c
+../../../src/obiblob_indexer.h
+../../../src/obiblob_indexer.c
+../../../src/obiview.h
+../../../src/obiview.c
+../../../src/hashtable.h
+../../../src/hashtable.c
+../../../src/linked_list.h
+../../../src/linked_list.c
+../../../src/obidmscolumn_array.h
+../../../src/obidmscolumn_array.c
+../../../src/obidmscolumn_blob.h
+../../../src/obidmscolumn_blob.c
+../../../src/obidmscolumn_idx.h
+../../../src/obidmscolumn_idx.c
+../../../src/obidmscolumn_bool.h
+../../../src/obidmscolumn_bool.c
+../../../src/obidmscolumn_char.h
+../../../src/obidmscolumn_char.c
+../../../src/obidmscolumn_float.h
+../../../src/obidmscolumn_float.c
+../../../src/obidmscolumn_int.h
+../../../src/obidmscolumn_int.c
+../../../src/obidmscolumn_qual.h
+../../../src/obidmscolumn_qual.c
+../../../src/obidmscolumn_seq.h
+../../../src/obidmscolumn_seq.c
+../../../src/obidmscolumn_str.h
+../../../src/obidmscolumn_str.c
+../../../src/array_indexer.h
+../../../src/array_indexer.c
+../../../src/char_str_indexer.h
+../../../src/char_str_indexer.c
+../../../src/dna_seq_indexer.h
+../../../src/dna_seq_indexer.c
+../../../src/encode.c
+../../../src/encode.h
+../../../src/uint8_indexer.c
+../../../src/uint8_indexer.h
+../../../src/build_reference_db.c
+../../../src/build_reference_db.h
+../../../src/kmer_similarity.c
+../../../src/kmer_similarity.h
+../../../src/obi_clean.c
+../../../src/obi_clean.h
+../../../src/obi_ecopcr.c
+../../../src/obi_ecopcr.h
+../../../src/obi_ecotag.c
+../../../src/obi_ecotag.h
+../../../src/obidms_taxonomy.c
+../../../src/obidms_taxonomy.h
+../../../src/obilittlebigman.c
+../../../src/obilittlebigman.h
+../../../src/_sse.h
+../../../src/obidebug.h
+../../../src/libecoPCR/libapat/CODES/dft_code.h
+../../../src/libecoPCR/libapat/CODES/dna_code.h
+../../../src/libecoPCR/libapat/CODES/prot_code.h
+../../../src/libecoPCR/libapat/apat_parse.c
+../../../src/libecoPCR/libapat/apat_search.c
+../../../src/libecoPCR/libapat/apat.h
+../../../src/libecoPCR/libapat/Gmach.h
+../../../src/libecoPCR/libapat/Gtypes.h
+../../../src/libecoPCR/libapat/libstki.c
+../../../src/libecoPCR/libapat/libstki.h
+../../../src/libecoPCR/libthermo/nnparams.h
+../../../src/libecoPCR/libthermo/nnparams.c
+../../../src/libecoPCR/ecoapat.c
+../../../src/libecoPCR/ecodna.c
+../../../src/libecoPCR/ecoError.c
+../../../src/libecoPCR/ecoMalloc.c
+../../../src/libecoPCR/ecoPCR.h

python/obitools3/commands/export.pyx

@@ -0,0 +1,69 @@
+#cython: language_level=3
+
+from obitools3.apps.progress cimport ProgressBar  # @UnresolvedImport
+from obitools3.uri.decode import open_uri
+from obitools3.apps.config import logger
+from obitools3.dms import DMS
+from obitools3.dms.obiseq import Nuc_Seq
+
+from obitools3.apps.optiongroups import addMinimalInputOption, \
+                                        addExportOutputOption
+
+import sys
+
+__title__="Export a view to a different file format"
+
+
+def addOptions(parser):
+    
+    addMinimalInputOption(parser)
+    addExportOutputOption(parser)
+
+
+def run(config):
+        
+    DMS.obi_atexit()
+    
+    logger("info", "obi export : exports a view to a different file format")
+    
+    # Open the input
+    input = open_uri(config['obi']['inputURI'])
+    if input is None:
+        raise Exception("Could not read input")
+    iview = input[1]
+            
+    # Open the output
+    output = open_uri(config['obi']['outputURI'],
+                      input=False)
+    if output is None:
+        raise Exception("Could not open output URI")
+
+    output_object = output[0]
+    writer = output[1]
+        
+     # Check that the input view has the type NUC_SEQS if needed    # TODO discuss, maybe bool property
+    if (output[2] == Nuc_Seq) and (iview.type != b"NUC_SEQS_VIEW") :  # Nuc_Seq_Stored? TODO
+        raise Exception("Error: the view to export in fasta or fastq format is not a NUC_SEQS view")
+   
+    # Initialize the progress bar
+    pb = ProgressBar(len(iview), config, seconde=5)
+    
+    i=0
+    for seq in iview :
+        pb(i)
+        try:
+            writer(seq)
+        except StopIteration:
+            break
+        i+=1
+
+    pb(i, force=True)
+    print("", file=sys.stderr)
+
+    # TODO save command in input dms?
+    
+    output_object.close()
+    iview.close()
+    input[0].close()
+
+    logger("info", "Done.")

python/obitools3/commands/grep.cfiles

@@ -0,0 +1,103 @@
+../../../src/obi_lcs.h
+../../../src/obi_lcs.c
+../../../src/obierrno.h
+../../../src/obierrno.c
+../../../src/upperband.h
+../../../src/upperband.c
+../../../src/sse_banded_LCS_alignment.h
+../../../src/sse_banded_LCS_alignment.c
+../../../src/obiblob.h
+../../../src/obiblob.c
+../../../src/utils.h
+../../../src/utils.c
+../../../src/obidms.h
+../../../src/obidms.c
+../../../src/libjson/json_utils.h
+../../../src/libjson/json_utils.c
+../../../src/libjson/cJSON.h
+../../../src/libjson/cJSON.c
+../../../src/obiavl.h
+../../../src/obiavl.c
+../../../src/bloom.h
+../../../src/bloom.c
+../../../src/crc64.h
+../../../src/crc64.c
+../../../src/murmurhash2.h
+../../../src/murmurhash2.c
+../../../src/obidmscolumn.h
+../../../src/obidmscolumn.c
+../../../src/obitypes.h
+../../../src/obitypes.c
+../../../src/obidmscolumndir.h
+../../../src/obidmscolumndir.c
+../../../src/obiblob_indexer.h
+../../../src/obiblob_indexer.c
+../../../src/obiview.h
+../../../src/obiview.c
+../../../src/hashtable.h
+../../../src/hashtable.c
+../../../src/linked_list.h
+../../../src/linked_list.c
+../../../src/obidmscolumn_array.h
+../../../src/obidmscolumn_array.c
+../../../src/obidmscolumn_blob.h
+../../../src/obidmscolumn_blob.c
+../../../src/obidmscolumn_idx.h
+../../../src/obidmscolumn_idx.c
+../../../src/obidmscolumn_bool.h
+../../../src/obidmscolumn_bool.c
+../../../src/obidmscolumn_char.h
+../../../src/obidmscolumn_char.c
+../../../src/obidmscolumn_float.h
+../../../src/obidmscolumn_float.c
+../../../src/obidmscolumn_int.h
+../../../src/obidmscolumn_int.c
+../../../src/obidmscolumn_qual.h
+../../../src/obidmscolumn_qual.c
+../../../src/obidmscolumn_seq.h
+../../../src/obidmscolumn_seq.c
+../../../src/obidmscolumn_str.h
+../../../src/obidmscolumn_str.c
+../../../src/array_indexer.h
+../../../src/array_indexer.c
+../../../src/char_str_indexer.h
+../../../src/char_str_indexer.c
+../../../src/dna_seq_indexer.h
+../../../src/dna_seq_indexer.c
+../../../src/encode.c
+../../../src/encode.h
+../../../src/uint8_indexer.c
+../../../src/uint8_indexer.h
+../../../src/build_reference_db.c
+../../../src/build_reference_db.h
+../../../src/kmer_similarity.c
+../../../src/kmer_similarity.h
+../../../src/obi_clean.c
+../../../src/obi_clean.h
+../../../src/obi_ecopcr.c
+../../../src/obi_ecopcr.h
+../../../src/obi_ecotag.c
+../../../src/obi_ecotag.h
+../../../src/obidms_taxonomy.c
+../../../src/obidms_taxonomy.h
+../../../src/obilittlebigman.c
+../../../src/obilittlebigman.h
+../../../src/_sse.h
+../../../src/obidebug.h
+../../../src/libecoPCR/libapat/CODES/dft_code.h
+../../../src/libecoPCR/libapat/CODES/dna_code.h
+../../../src/libecoPCR/libapat/CODES/prot_code.h
+../../../src/libecoPCR/libapat/apat_parse.c
+../../../src/libecoPCR/libapat/apat_search.c
+../../../src/libecoPCR/libapat/apat.h
+../../../src/libecoPCR/libapat/Gmach.h
+../../../src/libecoPCR/libapat/Gtypes.h
+../../../src/libecoPCR/libapat/libstki.c
+../../../src/libecoPCR/libapat/libstki.h
+../../../src/libecoPCR/libthermo/nnparams.h
+../../../src/libecoPCR/libthermo/nnparams.c
+../../../src/libecoPCR/ecoapat.c
+../../../src/libecoPCR/ecodna.c
+../../../src/libecoPCR/ecoError.c
+../../../src/libecoPCR/ecoMalloc.c
+../../../src/libecoPCR/ecoPCR.h

python/obitools3/commands/grep.pyx

@@ -0,0 +1,352 @@
+#cython: language_level=3
+
+from obitools3.apps.progress cimport ProgressBar  # @UnresolvedImport
+from obitools3.dms import DMS
+from obitools3.dms.view.view cimport View, Line_selection
+from obitools3.uri.decode import open_uri
+from obitools3.apps.optiongroups import addMinimalInputOption, addTaxonomyOption, addMinimalOutputOption
+from obitools3.dms.view import RollbackException
+from obitools3.apps.config import logger
+from obitools3.utils cimport tobytes, str2bytes
+
+from functools import reduce
+import time
+import re
+import sys
+
+ 
+__title__="Grep view lines that match the given predicates"
+
+
+# TODO should sequences that have a grepped attribute at None be grepped or not? (in obi1 they are but....)
+
+ 
+def addOptions(parser):
+    
+    addMinimalInputOption(parser)
+    addTaxonomyOption(parser)
+    addMinimalOutputOption(parser)
+
+    group=parser.add_argument_group("obi grep specific options")
+ 
+    group.add_argument("--predicate", "-p",
+                       action="append", dest="grep:grep_predicates",
+                       metavar="<PREDICATE>",
+                       default=None,
+                       type=str,
+                       help="Python boolean expression to be evaluated in the "
+                            "sequence/line context. The attribute name can be "
+                            "used in the expression as a variable name."
+                            "An extra variable named 'sequence' or 'line' refers"
+                            "to the sequence or line object itself. "
+                            "Several -p options can be used on the same "
+                            "commande line.")
+ 
+    group.add_argument("-S", "--sequence",
+                       action="store", dest="grep:seq_pattern",
+                       metavar="<REGULAR_PATTERN>",
+                       type=str,
+                       help="Regular expression pattern used to select "
+                            "the sequence. The pattern is case insensitive.")
+    
+    group.add_argument("-D", "--definition",
+                       action="store", dest="grep:def_pattern",
+                       metavar="<REGULAR_PATTERN>",
+                       type=str,
+                       help="Regular expression pattern used to select "
+                            "the definition of the sequence. The pattern is case insensitive.")
+    
+    group.add_argument("-I", "--identifier",
+                       action="store", dest="grep:id_pattern",
+                       metavar="<REGULAR_PATTERN>",
+                       type=str,
+                       help="Regular expression pattern used to select "
+                            "the identifier of the sequence. The pattern is case insensitive.")
+    
+    group.add_argument("--id-list",
+                       action="store", dest="grep:id_list",
+                       metavar="<FILE_NAME>",
+                       type=str,
+                       help="File containing the identifiers of the sequences to select.")
+
+    group.add_argument("-a", "--attribute",
+                       action="append", dest="grep:attribute_patterns",
+                       type=str,
+                       default=[],
+                       metavar="<ATTRIBUTE_NAME>:<REGULAR_PATTERN>",
+                       help="Regular expression pattern matched against "
+                            "the attributes of the sequence. "
+                            "The pattern is case sensitive. "
+                            "Several -a options can be used on the same "
+                            "command line.")
+    
+    group.add_argument("-A", "--has-attribute",
+                       action="append", dest="grep:attributes",
+                       type=str,
+                       default=[],
+                       metavar="<ATTRIBUTE_NAME>",
+                       help="Select records with the attribute <ATTRIBUTE_NAME> "
+                            "defined (not set to NA value). "
+                            "Several -a options can be used on the same "
+                            "command line.")
+    
+    group.add_argument("-L", "--lmax",
+                       action="store", dest="grep:lmax",
+                       metavar="<MAX_LENGTH>",
+                       type=int,
+                       help="Keep sequences shorter than MAX_LENGTH.")
+                             
+    group.add_argument("-l", "--lmin",
+                       action="store", dest="grep:lmin",
+                       metavar="<MIN_LENGTH>",
+                       type=int,
+                       help="Keep sequences longer than MIN_LENGTH.")
+    
+    group.add_argument("-v", "--invert-selection",
+                       action="store_true", dest="grep:invert_selection",
+                       default=False,
+                       help="Invert the selection.")
+
+
+    group=parser.add_argument_group("Taxonomy filtering specific options")  #TODO put somewhere else? not in grep
+ 
+    group.add_argument('--require-rank',
+                       action="append", dest="grep:required_ranks",
+                       metavar="<RANK_NAME>",
+                       type=str,
+                       default=[],
+                       help="Select sequences with a taxid that is or has "
+                            "a parent of rank <RANK_NAME>.")
+     
+    group.add_argument('-r', '--required',
+                       action="append", dest="grep:required_taxids",
+                       metavar="<TAXID>",
+                       type=int,
+                       default=[],
+                       help="Select the sequences having the ancestor of taxid <TAXID>. "
+                            "If several ancestors are specified (with \n'-r taxid1 -r taxid2'), "
+                            "the sequences having at least one of them are selected.")
+     
+    # TODO useless option equivalent to -r -v?
+    group.add_argument('-i','--ignore',
+                     action="append", dest="grep:ignored_taxids",
+                     metavar="<TAXID>",
+                     type=int,
+                     default=[],
+                     help="Ignore the sequences having the ancestor of taxid <TAXID>. "
+                          "If several ancestors are specified (with \n'-r taxid1 -r taxid2'), "
+                          "the sequences having at least one of them are ignored.")
+
+
+def Filter_generator(options, tax_filter):
+    #taxfilter = taxonomyFilterGenerator(options)
+    
+    # Initialize conditions
+    predicates = None
+    if "predicates" in options:
+        predicates = options["predicates"]
+    attributes = None
+    if "attributes" in options:
+        attributes = options["attributes"]
+    lmax = None
+    if "lmax" in options:
+        lmax = options["lmax"]
+    lmin = None
+    if "lmin" in options:
+        lmin = options["lmin"]
+    invert_selection = options["invert_selection"]
+    id_set = None
+    if "id_list" in options:
+        id_set = set(x.strip() for x in open(options["id_list"]))
+
+    # Initialize the regular expression patterns
+    seq_pattern = None
+    if "seq_pattern" in options:
+        seq_pattern = re.compile(tobytes(options["seq_pattern"]), re.I)
+    id_pattern = None
+    if "id_pattern" in options:
+        id_pattern = re.compile(tobytes(options["id_pattern"]))
+    def_pattern = None
+    if "def_pattern" in options:
+        def_pattern = re.compile(tobytes(options["def_pattern"]))
+    attribute_patterns={}
+    if "attribute_patterns" in options:
+        for p in options["attribute_patterns"]:
+            attribute, pattern = p.split(":", 1)
+            attribute_patterns[tobytes(attribute)] = re.compile(tobytes(pattern))
+    
+    def filter(line, loc_env):
+        cdef bint good = True
+        
+        if seq_pattern and hasattr(line, "seq"):
+            good = <bint>(seq_pattern.search(line.seq))
+        
+        if good and id_pattern and hasattr(line, "id"):
+            good = <bint>(id_pattern.search(line.id))
+            
+        if good and id_set is not None and hasattr(line, "id"):
+            good = line.id in id_set
+            
+        if good and def_pattern and hasattr(line, "definition"):
+            good = <bint>(def_pattern.search(line.definition))
+             
+        if good and attributes:  # TODO discuss that we test not None
+            good = reduce(lambda bint x, bint y: x and y,
+                           (line[attribute] is not None for attribute in attributes),
+                           True)
+             
+        if good and attribute_patterns:
+            good = (reduce(lambda bint x, bint y : x and y, 
+                        (line[attribute] is not None for attribute in attributes),
+                        True)
+                    and
+                    reduce(lambda bint x, bint y: x and y,
+                        (<bint>(attribute_patterns[attribute].search(tobytes(str(line[attribute]))))
+                        for attribute in attribute_patterns), 
+                        True)
+                   )
+             
+        if good and predicates:
+            good = (reduce(lambda bint x, bint y: x and y,
+                    (bool(eval(p, loc_env, line))
+                    for p in predicates), True))
+
+        if good and lmin:
+            good = len(line) >= lmin
+             
+        if good and lmax:
+            good = len(line) <= lmax
+         
+        if good:
+            good = tax_filter(line)
+       
+        if invert_selection :
+            good = not good
+
+        return good
+    
+    return filter
+
+
+def Taxonomy_filter_generator(taxo, options):
+    if taxo is not None:
+        def tax_filter(seq):
+            good = True
+            if b'TAXID' in seq and seq[b'TAXID'] is not None:   # TODO use macro
+                taxid = seq[b'TAXID']
+                if "required_ranks" in options and options["required_ranks"]:
+                    taxon_at_rank = reduce(lambda x,y: x and y,
+                                           (taxo.get_taxon_at_rank(seq[b'TAXID'], rank) is not None
+                                            for rank in options["required_ranks"]),
+                                           True)
+                    good = good and taxon_at_rank 
+                if "required_taxids" in options and options["required_taxids"]:
+                    good = good and reduce(lambda x,y: x or y,
+                                           (taxo.is_ancestor(r, taxid) 
+                                            for r in options["required_taxids"]),
+                                           False)
+                if "ignored_taxids" in options and options["ignored_taxids"]:
+                    good = good and not reduce(lambda x,y: x or y,
+                                               (taxo.is_ancestor(r,taxid) 
+                                                for r in options["ignored_taxids"]),
+                                               False)
+            return good
+    else:
+        def tax_filter(seq):
+            return True
+    return tax_filter
+
+
+def run(config):
+     
+    DMS.obi_atexit()
+    
+    logger("info", "obi grep")
+
+    # Open the input
+    input = open_uri(config["obi"]["inputURI"])
+    if input is None:
+        raise Exception("Could not read input view")
+    i_dms = input[0]
+    i_view = input[1]
+
+    # Open the output: only the DMS
+    output = open_uri(config['obi']['outputURI'],
+                      input=False,
+                      dms_only=True)
+    if output is None:
+        raise Exception("Could not create output view")
+    o_dms = output[0]
+    o_view_name_final = output[1]
+    o_view_name = o_view_name_final
+    
+    # If the input and output DMS are not the same, create output view in input DMS first, then export it
+    # to output DMS, making sure the temporary view name is unique in the input DMS 
+    if i_dms != o_dms:
+        i=0
+        while o_view_name in i_dms:
+            o_view_name = o_view_name_final+b"_"+str2bytes(str(i))
+            i+=1        
+
+    if 'taxoURI' in config['obi'] and config['obi']['taxoURI'] is not None:
+        taxo_uri = open_uri(config["obi"]["taxoURI"])
+        if taxo_uri is None:
+            raise Exception("Couldn't open taxonomy")
+        taxo = taxo_uri[1]
+    else :
+        taxo = None
+
+    # Initialize the progress bar
+    pb = ProgressBar(len(i_view), config, seconde=5)
+ 
+    # Apply filter
+    tax_filter = Taxonomy_filter_generator(taxo, config["grep"])
+    filter = Filter_generator(config["grep"], tax_filter)
+    selection = Line_selection(i_view)
+    for i in range(len(i_view)):
+        pb(i)
+        line = i_view[i]
+                 
+        loc_env = {"sequence": line, "line": line, "taxonomy": taxo}
+        
+        good = filter(line, loc_env)
+ 
+        if good :
+            selection.append(i)
+
+    pb(i, force=True)
+    print("", file=sys.stderr)
+
+    # Create output view with the line selection
+    try:
+        o_view = selection.materialize(o_view_name)
+    except Exception, e:
+        raise RollbackException("obi grep error, rollbacking view: "+str(e), o_view)
+    
+    # Save command config in View and DMS comments
+    command_line = " ".join(sys.argv[1:])
+    input_dms_name=[input[0].name]
+    input_view_name=[input[1].name]
+    if 'taxoURI' in config['obi'] and config['obi']['taxoURI'] is not None:
+        input_dms_name.append(config['obi']['taxoURI'].split("/")[-3])
+        input_view_name.append("taxonomy/"+config['obi']['taxoURI'].split("/")[-1])
+    o_view.write_config(config, "grep", command_line, input_dms_name=input_dms_name, input_view_name=input_view_name)
+    o_dms.record_command_line(command_line)
+
+    # If input and output DMS are not the same, export the temporary view to the output DMS
+    # and delete the temporary view in the input DMS
+    if i_dms != o_dms:
+        o_view.close()
+        View.import_view(i_dms.full_path[:-7], o_dms.full_path[:-7], o_view_name, o_view_name_final)
+        o_view = o_dms[o_view_name_final]
+
+    #print("\n\nOutput view:\n````````````", file=sys.stderr)
+    #print(repr(o_view), file=sys.stderr)
+
+    # If the input and the output DMS are different, delete the temporary imported view used to create the final view
+    if i_dms != o_dms:
+        View.delete_view(i_dms, o_view_name)
+        o_dms.close()
+    i_dms.close()
+
+    logger("info", "Done.")

python/obitools3/commands/head.cfiles

@@ -0,0 +1,103 @@
+../../../src/obi_lcs.h
+../../../src/obi_lcs.c
+../../../src/obierrno.h
+../../../src/obierrno.c
+../../../src/upperband.h
+../../../src/upperband.c
+../../../src/sse_banded_LCS_alignment.h
+../../../src/sse_banded_LCS_alignment.c
+../../../src/obiblob.h
+../../../src/obiblob.c
+../../../src/utils.h
+../../../src/utils.c
+../../../src/obidms.h
+../../../src/obidms.c
+../../../src/libjson/json_utils.h
+../../../src/libjson/json_utils.c
+../../../src/libjson/cJSON.h
+../../../src/libjson/cJSON.c
+../../../src/obiavl.h
+../../../src/obiavl.c
+../../../src/bloom.h
+../../../src/bloom.c
+../../../src/crc64.h
+../../../src/crc64.c
+../../../src/murmurhash2.h
+../../../src/murmurhash2.c
+../../../src/obidmscolumn.h
+../../../src/obidmscolumn.c
+../../../src/obitypes.h
+../../../src/obitypes.c
+../../../src/obidmscolumndir.h
+../../../src/obidmscolumndir.c
+../../../src/obiblob_indexer.h
+../../../src/obiblob_indexer.c
+../../../src/obiview.h
+../../../src/obiview.c
+../../../src/hashtable.h
+../../../src/hashtable.c
+../../../src/linked_list.h
+../../../src/linked_list.c
+../../../src/obidmscolumn_array.h
+../../../src/obidmscolumn_array.c
+../../../src/obidmscolumn_blob.h
+../../../src/obidmscolumn_blob.c
+../../../src/obidmscolumn_idx.h
+../../../src/obidmscolumn_idx.c
+../../../src/obidmscolumn_bool.h
+../../../src/obidmscolumn_bool.c
+../../../src/obidmscolumn_char.h
+../../../src/obidmscolumn_char.c
+../../../src/obidmscolumn_float.h
+../../../src/obidmscolumn_float.c
+../../../src/obidmscolumn_int.h
+../../../src/obidmscolumn_int.c
+../../../src/obidmscolumn_qual.h
+../../../src/obidmscolumn_qual.c
+../../../src/obidmscolumn_seq.h
+../../../src/obidmscolumn_seq.c
+../../../src/obidmscolumn_str.h
+../../../src/obidmscolumn_str.c
+../../../src/array_indexer.h
+../../../src/array_indexer.c
+../../../src/char_str_indexer.h
+../../../src/char_str_indexer.c
+../../../src/dna_seq_indexer.h
+../../../src/dna_seq_indexer.c
+../../../src/encode.c
+../../../src/encode.h
+../../../src/uint8_indexer.c
+../../../src/uint8_indexer.h
+../../../src/build_reference_db.c
+../../../src/build_reference_db.h
+../../../src/kmer_similarity.c
+../../../src/kmer_similarity.h
+../../../src/obi_clean.c
+../../../src/obi_clean.h
+../../../src/obi_ecopcr.c
+../../../src/obi_ecopcr.h
+../../../src/obi_ecotag.c
+../../../src/obi_ecotag.h
+../../../src/obidms_taxonomy.c
+../../../src/obidms_taxonomy.h
+../../../src/obilittlebigman.c
+../../../src/obilittlebigman.h
+../../../src/_sse.h
+../../../src/obidebug.h
+../../../src/libecoPCR/libapat/CODES/dft_code.h
+../../../src/libecoPCR/libapat/CODES/dna_code.h
+../../../src/libecoPCR/libapat/CODES/prot_code.h
+../../../src/libecoPCR/libapat/apat_parse.c
+../../../src/libecoPCR/libapat/apat_search.c
+../../../src/libecoPCR/libapat/apat.h
+../../../src/libecoPCR/libapat/Gmach.h
+../../../src/libecoPCR/libapat/Gtypes.h
+../../../src/libecoPCR/libapat/libstki.c
+../../../src/libecoPCR/libapat/libstki.h
+../../../src/libecoPCR/libthermo/nnparams.h
+../../../src/libecoPCR/libthermo/nnparams.c
+../../../src/libecoPCR/ecoapat.c
+../../../src/libecoPCR/ecodna.c
+../../../src/libecoPCR/ecoError.c
+../../../src/libecoPCR/ecoMalloc.c
+../../../src/libecoPCR/ecoPCR.h

python/obitools3/commands/head.pyx

@@ -0,0 +1,106 @@
+#cython: language_level=3
+
+from obitools3.apps.progress cimport ProgressBar  # @UnresolvedImport
+from obitools3.dms import DMS
+from obitools3.dms.view.view cimport View, Line_selection
+from obitools3.uri.decode import open_uri
+from obitools3.apps.optiongroups import addMinimalInputOption, addMinimalOutputOption
+from obitools3.dms.view import RollbackException
+from obitools3.apps.config import logger
+from obitools3.utils cimport str2bytes
+
+import time
+import sys
+ 
+
+__title__="Keep the N first lines of a view."
+
+ 
+def addOptions(parser):
+    
+    addMinimalInputOption(parser)
+    addMinimalOutputOption(parser)
+
+    group=parser.add_argument_group('obi head specific options')
+
+    group.add_argument('-n', '--sequence-count',
+                       action="store", dest="head:count",
+                       metavar='<N>',
+                       default=10,
+                       type=int,
+                       help="Number of first records to keep.")
+
+     
+def run(config):
+     
+    DMS.obi_atexit()
+    
+    logger("info", "obi head")
+
+    # Open the input
+    input = open_uri(config["obi"]["inputURI"])
+    if input is None:
+        raise Exception("Could not read input view")
+    i_dms = input[0]
+    i_view = input[1]
+
+    # Open the output: only the DMS
+    output = open_uri(config['obi']['outputURI'],
+                      input=False,
+                      dms_only=True)
+    if output is None:
+        raise Exception("Could not create output view")
+    o_dms = output[0]
+    o_view_name_final = output[1]
+    o_view_name = o_view_name_final
+    
+    # If the input and output DMS are not the same, create output view in input DMS first, then export it
+    # to output DMS, making sure the temporary view name is unique in the input DMS 
+    if i_dms != o_dms:
+        i=0
+        while o_view_name in i_dms:
+            o_view_name = o_view_name_final+b"_"+str2bytes(str(i))
+            i+=1        
+    
+    n = min(config['head']['count'], len(i_view))
+
+    # Initialize the progress bar
+    pb = ProgressBar(n, config, seconde=5)
+        
+    selection = Line_selection(i_view)
+    
+    for i in range(n):
+        pb(i)
+        selection.append(i)
+
+    pb(i, force=True)
+    print("", file=sys.stderr)
+
+    # Create output view with the line selection
+    try:
+        o_view = selection.materialize(o_view_name)
+    except Exception, e:
+        raise RollbackException("obi head error, rollbacking view: "+str(e), o_view)
+    
+    # Save command config in DMS comments
+    command_line = " ".join(sys.argv[1:])
+    o_view.write_config(config, "head", command_line, input_dms_name=[i_dms.name], input_view_name=[i_view.name])
+    o_dms.record_command_line(command_line)
+
+    # If input and output DMS are not the same, export the temporary view to the output DMS
+    # and delete the temporary view in the input DMS
+    if i_dms != o_dms:
+        o_view.close()
+        View.import_view(i_dms.full_path[:-7], o_dms.full_path[:-7], o_view_name, o_view_name_final)
+        o_view = o_dms[o_view_name_final]
+
+    #print("\n\nOutput view:\n````````````", file=sys.stderr)
+    #print(repr(view), file=sys.stderr)
+
+    # If the input and the output DMS are different, delete the temporary imported view used to create the final view
+    if i_dms != o_dms:
+        View.delete_view(i_dms, o_view_name)
+        o_dms.close()
+    i_dms.close()
+    
+    logger("info", "Done.")

python/obitools3/commands/history.cfiles

@@ -0,0 +1,103 @@
+../../../src/obi_lcs.h
+../../../src/obi_lcs.c
+../../../src/obierrno.h
+../../../src/obierrno.c
+../../../src/upperband.h
+../../../src/upperband.c
+../../../src/sse_banded_LCS_alignment.h
+../../../src/sse_banded_LCS_alignment.c
+../../../src/obiblob.h
+../../../src/obiblob.c
+../../../src/utils.h
+../../../src/utils.c
+../../../src/obidms.h
+../../../src/obidms.c
+../../../src/libjson/json_utils.h
+../../../src/libjson/json_utils.c
+../../../src/libjson/cJSON.h
+../../../src/libjson/cJSON.c
+../../../src/obiavl.h
+../../../src/obiavl.c
+../../../src/bloom.h
+../../../src/bloom.c
+../../../src/crc64.h
+../../../src/crc64.c
+../../../src/murmurhash2.h
+../../../src/murmurhash2.c
+../../../src/obidmscolumn.h
+../../../src/obidmscolumn.c
+../../../src/obitypes.h
+../../../src/obitypes.c
+../../../src/obidmscolumndir.h
+../../../src/obidmscolumndir.c
+../../../src/obiblob_indexer.h
+../../../src/obiblob_indexer.c
+../../../src/obiview.h
+../../../src/obiview.c
+../../../src/hashtable.h
+../../../src/hashtable.c
+../../../src/linked_list.h
+../../../src/linked_list.c
+../../../src/obidmscolumn_array.h
+../../../src/obidmscolumn_array.c
+../../../src/obidmscolumn_blob.h
+../../../src/obidmscolumn_blob.c
+../../../src/obidmscolumn_idx.h
+../../../src/obidmscolumn_idx.c
+../../../src/obidmscolumn_bool.h
+../../../src/obidmscolumn_bool.c
+../../../src/obidmscolumn_char.h
+../../../src/obidmscolumn_char.c
+../../../src/obidmscolumn_float.h
+../../../src/obidmscolumn_float.c
+../../../src/obidmscolumn_int.h
+../../../src/obidmscolumn_int.c
+../../../src/obidmscolumn_qual.h
+../../../src/obidmscolumn_qual.c
+../../../src/obidmscolumn_seq.h
+../../../src/obidmscolumn_seq.c
+../../../src/obidmscolumn_str.h
+../../../src/obidmscolumn_str.c
+../../../src/array_indexer.h
+../../../src/array_indexer.c
+../../../src/char_str_indexer.h
+../../../src/char_str_indexer.c
+../../../src/dna_seq_indexer.h
+../../../src/dna_seq_indexer.c
+../../../src/encode.c
+../../../src/encode.h
+../../../src/uint8_indexer.c
+../../../src/uint8_indexer.h
+../../../src/build_reference_db.c
+../../../src/build_reference_db.h
+../../../src/kmer_similarity.c
+../../../src/kmer_similarity.h
+../../../src/obi_clean.c
+../../../src/obi_clean.h
+../../../src/obi_ecopcr.c
+../../../src/obi_ecopcr.h
+../../../src/obi_ecotag.c
+../../../src/obi_ecotag.h
+../../../src/obidms_taxonomy.c
+../../../src/obidms_taxonomy.h
+../../../src/obilittlebigman.c
+../../../src/obilittlebigman.h
+../../../src/_sse.h
+../../../src/obidebug.h
+../../../src/libecoPCR/libapat/CODES/dft_code.h
+../../../src/libecoPCR/libapat/CODES/dna_code.h
+../../../src/libecoPCR/libapat/CODES/prot_code.h
+../../../src/libecoPCR/libapat/apat_parse.c
+../../../src/libecoPCR/libapat/apat_search.c
+../../../src/libecoPCR/libapat/apat.h
+../../../src/libecoPCR/libapat/Gmach.h
+../../../src/libecoPCR/libapat/Gtypes.h
+../../../src/libecoPCR/libapat/libstki.c
+../../../src/libecoPCR/libapat/libstki.h
+../../../src/libecoPCR/libthermo/nnparams.h
+../../../src/libecoPCR/libthermo/nnparams.c
+../../../src/libecoPCR/ecoapat.c
+../../../src/libecoPCR/ecodna.c
+../../../src/libecoPCR/ecoError.c
+../../../src/libecoPCR/ecoMalloc.c
+../../../src/libecoPCR/ecoPCR.h

python/obitools3/commands/history.pyx

@@ -0,0 +1,57 @@
+#cython: language_level=3
+
+from obitools3.apps.optiongroups import addMinimalInputOption
+from obitools3.uri.decode import open_uri
+from obitools3.dms import DMS
+from obitools3.dms.view import View
+from obitools3.utils cimport bytes2str
+
+ 
+__title__="Command line histories and view history graphs"
+ 
+
+def addOptions(parser):
+
+    addMinimalInputOption(parser)
+ 
+    group=parser.add_argument_group('obi history specific options')
+ 
+    group.add_argument('--bash', '-b',
+                     action="store_const", dest="history:format",
+                     default="bash",
+                     const="bash",
+                     help="Print history in bash format")
+
+    group.add_argument('--dot', '-d',
+                     action="store_const", dest="history:format",
+                     default="bash",
+                     const="dot",
+                     help="Print history in DOT format (default: bash format)")
+
+    group.add_argument('--ascii', '-a',
+                     action="store_const", dest="history:format",
+                     default="bash",
+                     const="ascii",
+                     help="Print history in ASCII format (only for views; default: bash format)")
+ 
+
+def run(config):
+    
+    cdef object entries
+    
+    DMS.obi_atexit()
+    
+    input = open_uri(config['obi']['inputURI'])
+       
+    entries = input[1]
+    
+    if config['history']['format'] == "bash" :
+        print(bytes2str(entries.bash_history))
+    elif config['history']['format'] == "dot" :
+        print(bytes2str(entries.dot_history_graph))
+    elif config['history']['format'] == "ascii" :
+        if isinstance(entries, View):
+            print(bytes2str(entries.ascii_history_graph))
+        else:
+            raise Exception("ASCII history only available for views")
+            

python/obitools3/commands/import.cfiles

@@ -0,0 +1,103 @@
+../../../src/obi_lcs.h
+../../../src/obi_lcs.c
+../../../src/obierrno.h
+../../../src/obierrno.c
+../../../src/upperband.h
+../../../src/upperband.c
+../../../src/sse_banded_LCS_alignment.h
+../../../src/sse_banded_LCS_alignment.c
+../../../src/obiblob.h
+../../../src/obiblob.c
+../../../src/utils.h
+../../../src/utils.c
+../../../src/obidms.h
+../../../src/obidms.c
+../../../src/libjson/json_utils.h
+../../../src/libjson/json_utils.c
+../../../src/libjson/cJSON.h
+../../../src/libjson/cJSON.c
+../../../src/obiavl.h
+../../../src/obiavl.c
+../../../src/bloom.h
+../../../src/bloom.c
+../../../src/crc64.h
+../../../src/crc64.c
+../../../src/murmurhash2.h
+../../../src/murmurhash2.c
+../../../src/obidmscolumn.h
+../../../src/obidmscolumn.c
+../../../src/obitypes.h
+../../../src/obitypes.c
+../../../src/obidmscolumndir.h
+../../../src/obidmscolumndir.c
+../../../src/obiblob_indexer.h
+../../../src/obiblob_indexer.c
+../../../src/obiview.h
+../../../src/obiview.c
+../../../src/hashtable.h
+../../../src/hashtable.c
+../../../src/linked_list.h
+../../../src/linked_list.c
+../../../src/obidmscolumn_array.h
+../../../src/obidmscolumn_array.c
+../../../src/obidmscolumn_blob.h
+../../../src/obidmscolumn_blob.c
+../../../src/obidmscolumn_idx.h
+../../../src/obidmscolumn_idx.c
+../../../src/obidmscolumn_bool.h
+../../../src/obidmscolumn_bool.c
+../../../src/obidmscolumn_char.h
+../../../src/obidmscolumn_char.c
+../../../src/obidmscolumn_float.h
+../../../src/obidmscolumn_float.c
+../../../src/obidmscolumn_int.h
+../../../src/obidmscolumn_int.c
+../../../src/obidmscolumn_qual.h
+../../../src/obidmscolumn_qual.c
+../../../src/obidmscolumn_seq.h
+../../../src/obidmscolumn_seq.c
+../../../src/obidmscolumn_str.h
+../../../src/obidmscolumn_str.c
+../../../src/array_indexer.h
+../../../src/array_indexer.c
+../../../src/char_str_indexer.h
+../../../src/char_str_indexer.c
+../../../src/dna_seq_indexer.h
+../../../src/dna_seq_indexer.c
+../../../src/encode.c
+../../../src/encode.h
+../../../src/uint8_indexer.c
+../../../src/uint8_indexer.h
+../../../src/build_reference_db.c
+../../../src/build_reference_db.h
+../../../src/kmer_similarity.c
+../../../src/kmer_similarity.h
+../../../src/obi_clean.c
+../../../src/obi_clean.h
+../../../src/obi_ecopcr.c
+../../../src/obi_ecopcr.h
+../../../src/obi_ecotag.c
+../../../src/obi_ecotag.h
+../../../src/obidms_taxonomy.c
+../../../src/obidms_taxonomy.h
+../../../src/obilittlebigman.c
+../../../src/obilittlebigman.h
+../../../src/_sse.h
+../../../src/obidebug.h
+../../../src/libecoPCR/libapat/CODES/dft_code.h
+../../../src/libecoPCR/libapat/CODES/dna_code.h
+../../../src/libecoPCR/libapat/CODES/prot_code.h
+../../../src/libecoPCR/libapat/apat_parse.c
+../../../src/libecoPCR/libapat/apat_search.c
+../../../src/libecoPCR/libapat/apat.h
+../../../src/libecoPCR/libapat/Gmach.h
+../../../src/libecoPCR/libapat/Gtypes.h
+../../../src/libecoPCR/libapat/libstki.c
+../../../src/libecoPCR/libapat/libstki.h
+../../../src/libecoPCR/libthermo/nnparams.h
+../../../src/libecoPCR/libthermo/nnparams.c
+../../../src/libecoPCR/ecoapat.c
+../../../src/libecoPCR/ecodna.c
+../../../src/libecoPCR/ecoError.c
+../../../src/libecoPCR/ecoMalloc.c
+../../../src/libecoPCR/ecoPCR.h

python/obitools3/commands/import.pyx

@@ -0,0 +1,301 @@
+#cython: language_level=3
+
+import sys
+import os
+
+from obitools3.apps.progress cimport ProgressBar  # @UnresolvedImport
+from obitools3.dms.view.view cimport View
+from obitools3.dms.view import RollbackException
+from obitools3.dms.view.typed_view.view_NUC_SEQS cimport View_NUC_SEQS
+from obitools3.dms.column.column cimport Column
+from obitools3.dms.obiseq cimport Nuc_Seq
+from obitools3.dms import DMS
+from obitools3.dms.taxo.taxo cimport Taxonomy
+
+
+from obitools3.utils cimport tobytes, \
+                             get_obitype, \
+                             update_obitype
+
+from obitools3.dms.capi.obiview cimport VIEW_TYPE_NUC_SEQS, \
+                                        NUC_SEQUENCE_COLUMN, \
+                                        ID_COLUMN, \
+                                        DEFINITION_COLUMN, \
+                                        QUALITY_COLUMN, \
+                                        COUNT_COLUMN, \
+                                        TAXID_COLUMN
+                                        
+from obitools3.dms.capi.obitypes cimport obitype_t, \
+                                         OBI_VOID, \
+                                         OBI_QUAL
+
+from obitools3.dms.capi.obierrno cimport obi_errno
+
+from obitools3.apps.optiongroups import addImportInputOption, \
+                                        addTabularInputOption, \
+                                        addTaxdumpInputOption, \
+                                        addMinimalOutputOption
+
+from obitools3.uri.decode import open_uri
+
+from obitools3.apps.config import logger
+
+__title__="Imports sequences from different formats into a DMS"
+ 
+ 
+default_config = {   'destview'     : None,
+                     'skip'         : 0,
+                     'only'         : None,
+                     'skiperror'    : False,
+                     'seqinformat'  : None,
+                     'moltype'      : 'nuc',
+                     'source'     : None
+                 }
+
+def addOptions(parser):
+    
+    addImportInputOption(parser)
+    addTabularInputOption(parser)
+    addTaxdumpInputOption(parser)
+    addMinimalOutputOption(parser)
+
+
+def run(config):
+    
+    cdef   tuple       input
+    cdef   tuple       output 
+    cdef   int         i
+    cdef   type        value_type
+    cdef   obitype_t   value_obitype
+    cdef   obitype_t   old_type
+    cdef   obitype_t   new_type
+    cdef   bint        get_quality
+    cdef   bint        NUC_SEQS_view
+    cdef   int         nb_elts
+    cdef   object      d
+    cdef   View        view
+    cdef   object      entries
+    cdef   object      entry
+    cdef   Column      id_col
+    cdef   Column      def_col
+    cdef   Column      seq_col
+    cdef   Column      qual_col
+    cdef   Column      old_column
+    cdef   bint        rewrite
+    cdef   dict        dcols
+    cdef   int         skipping
+    cdef   bytes       tag
+    cdef   object      value
+    cdef   list        elt_names
+    cdef   int         old_nb_elements_per_line
+    cdef   int         new_nb_elements_per_line
+    cdef   list        old_elements_names
+    cdef   list        new_elements_names
+    cdef   ProgressBar pb
+    global             obi_errno
+        
+    DMS.obi_atexit()
+    
+    logger("info", "obi import: imports an object (file(s), obiview, taxonomy...) into a DMS")
+    
+    entry_count = -1
+    
+    if not config['obi']['taxdump']:
+        input = open_uri(config['obi']['inputURI'])
+        if input is None:  # TODO check for bytes instead now?
+            raise Exception("Could not open input URI")
+        
+        entry_count = input[4]
+        logger("info", "Importing %d entries", entry_count)
+        
+        # TODO a bit dirty?
+        if input[2]==Nuc_Seq:
+            v = View_NUC_SEQS
+        else:
+            v = View 
+    else:
+        v = None
+
+    output = open_uri(config['obi']['outputURI'],
+                      input=False,
+                      newviewtype=v)
+    if output is None:
+        raise Exception("Could not create output view")
+        
+    # Read taxdump
+    if config['obi']['taxdump']:  # The input is a taxdump to import in a DMS
+        taxo = Taxonomy.open_taxdump(output[0], config['obi']['inputURI'])
+        taxo.write(output[1])
+        taxo.close()
+        output[0].record_command_line(" ".join(sys.argv[1:]))
+        output[0].close()
+        return
+    
+    if entry_count >= 0:
+        pb = ProgressBar(entry_count, config, seconde=5)
+    else:
+        pb = None
+    
+    entries = input[1]
+        
+    NUC_SEQS_view = False
+    if isinstance(output[1], View) :
+        view = output[1]
+        if output[2] == View_NUC_SEQS :
+            NUC_SEQS_view = True
+    else: 
+        raise NotImplementedError()
+    
+    # Save basic columns in variables for optimization
+    if NUC_SEQS_view :
+        id_col = view[ID_COLUMN]
+        def_col = view[DEFINITION_COLUMN]
+        seq_col = view[NUC_SEQUENCE_COLUMN]
+        
+    dcols = {}
+        
+    i = 0
+    for entry in entries :
+        
+        if entry is None:  # error or exception handled at lower level, not raised because Python generators can't resume after any exception is raised
+            if config['obi']['skiperror']:
+                i-=1
+                continue
+            else:
+                raise RollbackException("obi import error, rollbacking view", view)
+        
+        if pb is not None:
+            pb(i)
+                        
+        if NUC_SEQS_view: 
+            id_col[i] = entry.id
+            def_col[i] = entry.definition
+            seq_col[i] = entry.seq
+            # Check if there is a sequencing quality associated by checking the first entry    # TODO haven't found a more robust solution yet
+            if i == 0:
+                get_quality = QUALITY_COLUMN in entry
+                if get_quality:
+                    Column.new_column(view, QUALITY_COLUMN, OBI_QUAL)
+                    qual_col = view[QUALITY_COLUMN]
+            if get_quality:
+                qual_col[i] = entry.quality
+         
+        for tag in entry :
+            
+            if tag != ID_COLUMN and tag != DEFINITION_COLUMN and tag != NUC_SEQUENCE_COLUMN and tag != QUALITY_COLUMN :  # TODO dirty 
+                                
+                value = entry[tag]
+                if tag == b"taxid":
+                    tag = TAXID_COLUMN
+                if tag == b"count":
+                    tag = COUNT_COLUMN
+                    
+                if tag not in dcols :
+                     
+                    value_type = type(value)
+                    nb_elts = 1
+                    value_obitype = OBI_VOID
+                     
+                    if value_type == dict or value_type == list :
+                        nb_elts = len(value)
+                        elt_names = list(value)
+                    else :
+                        nb_elts = 1
+                        elt_names = None
+                     
+                    value_obitype = get_obitype(value)
+                     
+                    if value_obitype != OBI_VOID :
+                        dcols[tag] = (Column.new_column(view, tag, value_obitype, nb_elements_per_line=nb_elts, elements_names=elt_names), value_obitype)
+                                                 
+                        # Fill value
+                        dcols[tag][0][i] = value
+                     
+                    # TODO else log error?
+ 
+                else :
+         
+                    rewrite = False
+ 
+                    # Check type adequation
+                    old_type = dcols[tag][1]
+                    new_type = OBI_VOID
+                    new_type = update_obitype(old_type, value)
+                    if old_type != new_type :
+                        rewrite = True
+ 
+                    try:
+                        # Fill value
+                        dcols[tag][0][i] = value
+                     
+                    except IndexError :
+                                                 
+                        value_type = type(value)
+                        old_column = dcols[tag][0]
+                        old_nb_elements_per_line = old_column.nb_elements_per_line
+                        new_nb_elements_per_line = 0
+                        old_elements_names = old_column.elements_names
+                        new_elements_names = None
+     
+                        #####################################################################
+                         
+                        # Check the length and keys of column lines if needed
+                        if value_type == dict :    # Check dictionary keys
+                            for k in value :
+                                if k not in old_elements_names :
+                                    new_elements_names = list(set(old_elements_names+[tobytes(k) for k in value]))
+                                    rewrite = True
+                                    break
+                         
+                        elif value_type == list or value_type == tuple :  # Check vector length
+                            if old_nb_elements_per_line < len(value) :
+                                new_nb_elements_per_line = len(value)
+                                rewrite = True
+                         
+                        #####################################################################
+                         
+                        if rewrite :
+                            if new_nb_elements_per_line == 0 and new_elements_names is not None :
+                                new_nb_elements_per_line = len(new_elements_names)
+                             
+                            # Reset obierrno 
+                            obi_errno = 0
+ 
+                            dcols[tag] = (view.rewrite_column_with_diff_attributes(old_column.name, 
+                                                                                   new_data_type=new_type, 
+                                                                                   new_nb_elements_per_line=new_nb_elements_per_line,
+                                                                                   new_elements_names=new_elements_names,
+                                                                                   rewrite_last_line=False), 
+                                          value_obitype)
+                             
+                            # Update the dictionary:
+                            for t in dcols :
+                                dcols[t] = (view[t], dcols[t][1])
+                             
+                            # Fill value
+                            dcols[tag][0][i] = value
+                                    
+        i+=1
+ 
+    if pb is not None:
+        pb(i, force=True)
+        print("", file=sys.stderr)
+    
+    # Save command config in View and DMS comments
+    command_line = " ".join(sys.argv[1:])
+    view.write_config(config, "import", command_line, input_str=[os.path.abspath(config['obi']['inputURI'])])
+    output[0].record_command_line(command_line)
+
+    #print("\n\nOutput view:\n````````````", file=sys.stderr)
+    #print(repr(view), file=sys.stderr)
+    
+    try:
+        input[0].close()
+    except AttributeError:
+        pass
+    try:
+        output[0].close()
+    except AttributeError:
+        pass
+
+    logger("info", "Done.")

python/obitools3/commands/less.cfiles

@@ -0,0 +1,103 @@
+../../../src/obi_lcs.h
+../../../src/obi_lcs.c
+../../../src/obierrno.h
+../../../src/obierrno.c
+../../../src/upperband.h
+../../../src/upperband.c
+../../../src/sse_banded_LCS_alignment.h
+../../../src/sse_banded_LCS_alignment.c
+../../../src/obiblob.h
+../../../src/obiblob.c
+../../../src/utils.h
+../../../src/utils.c
+../../../src/obidms.h
+../../../src/obidms.c
+../../../src/libjson/json_utils.h
+../../../src/libjson/json_utils.c
+../../../src/libjson/cJSON.h
+../../../src/libjson/cJSON.c
+../../../src/obiavl.h
+../../../src/obiavl.c
+../../../src/bloom.h
+../../../src/bloom.c
+../../../src/crc64.h
+../../../src/crc64.c
+../../../src/murmurhash2.h
+../../../src/murmurhash2.c
+../../../src/obidmscolumn.h
+../../../src/obidmscolumn.c
+../../../src/obitypes.h
+../../../src/obitypes.c
+../../../src/obidmscolumndir.h
+../../../src/obidmscolumndir.c
+../../../src/obiblob_indexer.h
+../../../src/obiblob_indexer.c
+../../../src/obiview.h
+../../../src/obiview.c
+../../../src/hashtable.h
+../../../src/hashtable.c
+../../../src/linked_list.h
+../../../src/linked_list.c
+../../../src/obidmscolumn_array.h
+../../../src/obidmscolumn_array.c
+../../../src/obidmscolumn_blob.h
+../../../src/obidmscolumn_blob.c
+../../../src/obidmscolumn_idx.h
+../../../src/obidmscolumn_idx.c
+../../../src/obidmscolumn_bool.h
+../../../src/obidmscolumn_bool.c
+../../../src/obidmscolumn_char.h
+../../../src/obidmscolumn_char.c
+../../../src/obidmscolumn_float.h
+../../../src/obidmscolumn_float.c
+../../../src/obidmscolumn_int.h
+../../../src/obidmscolumn_int.c
+../../../src/obidmscolumn_qual.h
+../../../src/obidmscolumn_qual.c
+../../../src/obidmscolumn_seq.h
+../../../src/obidmscolumn_seq.c
+../../../src/obidmscolumn_str.h
+../../../src/obidmscolumn_str.c
+../../../src/array_indexer.h
+../../../src/array_indexer.c
+../../../src/char_str_indexer.h
+../../../src/char_str_indexer.c
+../../../src/dna_seq_indexer.h
+../../../src/dna_seq_indexer.c
+../../../src/encode.c
+../../../src/encode.h
+../../../src/uint8_indexer.c
+../../../src/uint8_indexer.h
+../../../src/build_reference_db.c
+../../../src/build_reference_db.h
+../../../src/kmer_similarity.c
+../../../src/kmer_similarity.h
+../../../src/obi_clean.c
+../../../src/obi_clean.h
+../../../src/obi_ecopcr.c
+../../../src/obi_ecopcr.h
+../../../src/obi_ecotag.c
+../../../src/obi_ecotag.h
+../../../src/obidms_taxonomy.c
+../../../src/obidms_taxonomy.h
+../../../src/obilittlebigman.c
+../../../src/obilittlebigman.h
+../../../src/_sse.h
+../../../src/obidebug.h
+../../../src/libecoPCR/libapat/CODES/dft_code.h
+../../../src/libecoPCR/libapat/CODES/dna_code.h
+../../../src/libecoPCR/libapat/CODES/prot_code.h
+../../../src/libecoPCR/libapat/apat_parse.c
+../../../src/libecoPCR/libapat/apat_search.c
+../../../src/libecoPCR/libapat/apat.h
+../../../src/libecoPCR/libapat/Gmach.h
+../../../src/libecoPCR/libapat/Gtypes.h
+../../../src/libecoPCR/libapat/libstki.c
+../../../src/libecoPCR/libapat/libstki.h
+../../../src/libecoPCR/libthermo/nnparams.h
+../../../src/libecoPCR/libthermo/nnparams.c
+../../../src/libecoPCR/ecoapat.c
+../../../src/libecoPCR/ecodna.c
+../../../src/libecoPCR/ecoError.c
+../../../src/libecoPCR/ecoMalloc.c
+../../../src/libecoPCR/ecoPCR.h

python/obitools3/commands/less.pyx

@@ -0,0 +1,44 @@
+#cython: language_level=3
+
+from obitools3.apps.optiongroups import addMinimalInputOption
+from obitools3.uri.decode import open_uri
+from obitools3.dms import DMS
+
+ 
+__title__="Less equivalent"
+ 
+
+def addOptions(parser):
+
+    addMinimalInputOption(parser)
+ 
+    group=parser.add_argument_group('obi less specific options')
+ 
+    group.add_argument('--print', '-n',
+                     action="store", dest="less:print",
+                     metavar='<N>',
+                     default=10,
+                     type=int,
+                     help="Print N entries (default: 10)")
+ 
+
+def run(config):
+    
+    cdef object entries
+    cdef int    n
+    
+    DMS.obi_atexit()
+    
+    input = open_uri(config['obi']['inputURI'])
+       
+    entries = input[1]
+    
+    if config['less']['print'] > len(entries) :
+        n = len(entries)
+    else :
+        n = config['less']['print']
+        
+    # Print
+    for i in range(n) :
+        print(repr(entries[i]))
+

python/obitools3/commands/ls.cfiles

@@ -0,0 +1,103 @@
+../../../src/obi_lcs.h
+../../../src/obi_lcs.c
+../../../src/obierrno.h
+../../../src/obierrno.c
+../../../src/upperband.h
+../../../src/upperband.c
+../../../src/sse_banded_LCS_alignment.h
+../../../src/sse_banded_LCS_alignment.c
+../../../src/obiblob.h
+../../../src/obiblob.c
+../../../src/utils.h
+../../../src/utils.c
+../../../src/obidms.h
+../../../src/obidms.c
+../../../src/libjson/json_utils.h
+../../../src/libjson/json_utils.c
+../../../src/libjson/cJSON.h
+../../../src/libjson/cJSON.c
+../../../src/obiavl.h
+../../../src/obiavl.c
+../../../src/bloom.h
+../../../src/bloom.c
+../../../src/crc64.h
+../../../src/crc64.c
+../../../src/murmurhash2.h
+../../../src/murmurhash2.c
+../../../src/obidmscolumn.h
+../../../src/obidmscolumn.c
+../../../src/obitypes.h
+../../../src/obitypes.c
+../../../src/obidmscolumndir.h
+../../../src/obidmscolumndir.c
+../../../src/obiblob_indexer.h
+../../../src/obiblob_indexer.c
+../../../src/obiview.h
+../../../src/obiview.c
+../../../src/hashtable.h
+../../../src/hashtable.c
+../../../src/linked_list.h
+../../../src/linked_list.c
+../../../src/obidmscolumn_array.h
+../../../src/obidmscolumn_array.c
+../../../src/obidmscolumn_blob.h
+../../../src/obidmscolumn_blob.c
+../../../src/obidmscolumn_idx.h
+../../../src/obidmscolumn_idx.c
+../../../src/obidmscolumn_bool.h
+../../../src/obidmscolumn_bool.c
+../../../src/obidmscolumn_char.h
+../../../src/obidmscolumn_char.c
+../../../src/obidmscolumn_float.h
+../../../src/obidmscolumn_float.c
+../../../src/obidmscolumn_int.h
+../../../src/obidmscolumn_int.c
+../../../src/obidmscolumn_qual.h
+../../../src/obidmscolumn_qual.c
+../../../src/obidmscolumn_seq.h
+../../../src/obidmscolumn_seq.c
+../../../src/obidmscolumn_str.h
+../../../src/obidmscolumn_str.c
+../../../src/array_indexer.h
+../../../src/array_indexer.c
+../../../src/char_str_indexer.h
+../../../src/char_str_indexer.c
+../../../src/dna_seq_indexer.h
+../../../src/dna_seq_indexer.c
+../../../src/encode.c
+../../../src/encode.h
+../../../src/uint8_indexer.c
+../../../src/uint8_indexer.h
+../../../src/build_reference_db.c
+../../../src/build_reference_db.h
+../../../src/kmer_similarity.c
+../../../src/kmer_similarity.h
+../../../src/obi_clean.c
+../../../src/obi_clean.h
+../../../src/obi_ecopcr.c
+../../../src/obi_ecopcr.h
+../../../src/obi_ecotag.c
+../../../src/obi_ecotag.h
+../../../src/obidms_taxonomy.c
+../../../src/obidms_taxonomy.h
+../../../src/obilittlebigman.c
+../../../src/obilittlebigman.h
+../../../src/_sse.h
+../../../src/obidebug.h
+../../../src/libecoPCR/libapat/CODES/dft_code.h
+../../../src/libecoPCR/libapat/CODES/dna_code.h
+../../../src/libecoPCR/libapat/CODES/prot_code.h
+../../../src/libecoPCR/libapat/apat_parse.c
+../../../src/libecoPCR/libapat/apat_search.c
+../../../src/libecoPCR/libapat/apat.h
+../../../src/libecoPCR/libapat/Gmach.h
+../../../src/libecoPCR/libapat/Gtypes.h
+../../../src/libecoPCR/libapat/libstki.c
+../../../src/libecoPCR/libapat/libstki.h
+../../../src/libecoPCR/libthermo/nnparams.h
+../../../src/libecoPCR/libthermo/nnparams.c
+../../../src/libecoPCR/ecoapat.c
+../../../src/libecoPCR/ecodna.c
+../../../src/libecoPCR/ecoError.c
+../../../src/libecoPCR/ecoMalloc.c
+../../../src/libecoPCR/ecoPCR.h

python/obitools3/commands/ls.pyx

@@ -0,0 +1,28 @@
+#cython: language_level=3
+
+from obitools3.uri.decode import open_uri
+from obitools3.apps.config import logger
+from obitools3.dms import DMS
+from obitools3.apps.optiongroups import addMinimalInputOption
+
+ 
+__title__="Print a preview of a DMS, view, column...."
+
+
+def addOptions(parser):    
+    addMinimalInputOption(parser)
+
+
+def run(config):
+
+    DMS.obi_atexit()
+    
+    logger("info", "obi ls")
+
+    # Open the input
+    input = open_uri(config['obi']['inputURI'])
+    if input is None:
+        raise Exception("Could not read input")
+    
+    print(repr(input[1]))
+     

python/obitools3/commands/ngsfilter.cfiles

@@ -0,0 +1,103 @@
+../../../src/obi_lcs.h
+../../../src/obi_lcs.c
+../../../src/obierrno.h
+../../../src/obierrno.c
+../../../src/upperband.h
+../../../src/upperband.c
+../../../src/sse_banded_LCS_alignment.h
+../../../src/sse_banded_LCS_alignment.c
+../../../src/obiblob.h
+../../../src/obiblob.c
+../../../src/utils.h
+../../../src/utils.c
+../../../src/obidms.h
+../../../src/obidms.c
+../../../src/libjson/json_utils.h
+../../../src/libjson/json_utils.c
+../../../src/libjson/cJSON.h
+../../../src/libjson/cJSON.c
+../../../src/obiavl.h
+../../../src/obiavl.c
+../../../src/bloom.h
+../../../src/bloom.c
+../../../src/crc64.h
+../../../src/crc64.c
+../../../src/murmurhash2.h
+../../../src/murmurhash2.c
+../../../src/obidmscolumn.h
+../../../src/obidmscolumn.c
+../../../src/obitypes.h
+../../../src/obitypes.c
+../../../src/obidmscolumndir.h
+../../../src/obidmscolumndir.c
+../../../src/obiblob_indexer.h
+../../../src/obiblob_indexer.c
+../../../src/obiview.h
+../../../src/obiview.c
+../../../src/hashtable.h
+../../../src/hashtable.c
+../../../src/linked_list.h
+../../../src/linked_list.c
+../../../src/obidmscolumn_array.h
+../../../src/obidmscolumn_array.c
+../../../src/obidmscolumn_blob.h
+../../../src/obidmscolumn_blob.c
+../../../src/obidmscolumn_idx.h
+../../../src/obidmscolumn_idx.c
+../../../src/obidmscolumn_bool.h
+../../../src/obidmscolumn_bool.c
+../../../src/obidmscolumn_char.h
+../../../src/obidmscolumn_char.c
+../../../src/obidmscolumn_float.h
+../../../src/obidmscolumn_float.c
+../../../src/obidmscolumn_int.h
+../../../src/obidmscolumn_int.c
+../../../src/obidmscolumn_qual.h
+../../../src/obidmscolumn_qual.c
+../../../src/obidmscolumn_seq.h
+../../../src/obidmscolumn_seq.c
+../../../src/obidmscolumn_str.h
+../../../src/obidmscolumn_str.c
+../../../src/array_indexer.h
+../../../src/array_indexer.c
+../../../src/char_str_indexer.h
+../../../src/char_str_indexer.c
+../../../src/dna_seq_indexer.h
+../../../src/dna_seq_indexer.c
+../../../src/encode.c
+../../../src/encode.h
+../../../src/uint8_indexer.c
+../../../src/uint8_indexer.h
+../../../src/build_reference_db.c
+../../../src/build_reference_db.h
+../../../src/kmer_similarity.c
+../../../src/kmer_similarity.h
+../../../src/obi_clean.c
+../../../src/obi_clean.h
+../../../src/obi_ecopcr.c
+../../../src/obi_ecopcr.h
+../../../src/obi_ecotag.c
+../../../src/obi_ecotag.h
+../../../src/obidms_taxonomy.c
+../../../src/obidms_taxonomy.h
+../../../src/obilittlebigman.c
+../../../src/obilittlebigman.h
+../../../src/_sse.h
+../../../src/obidebug.h
+../../../src/libecoPCR/libapat/CODES/dft_code.h
+../../../src/libecoPCR/libapat/CODES/dna_code.h
+../../../src/libecoPCR/libapat/CODES/prot_code.h
+../../../src/libecoPCR/libapat/apat_parse.c
+../../../src/libecoPCR/libapat/apat_search.c
+../../../src/libecoPCR/libapat/apat.h
+../../../src/libecoPCR/libapat/Gmach.h
+../../../src/libecoPCR/libapat/Gtypes.h
+../../../src/libecoPCR/libapat/libstki.c
+../../../src/libecoPCR/libapat/libstki.h
+../../../src/libecoPCR/libthermo/nnparams.h
+../../../src/libecoPCR/libthermo/nnparams.c
+../../../src/libecoPCR/ecoapat.c
+../../../src/libecoPCR/ecodna.c
+../../../src/libecoPCR/ecoError.c
+../../../src/libecoPCR/ecoMalloc.c
+../../../src/libecoPCR/ecoPCR.h

python/obitools3/commands/ngsfilter.pyx

@@ -0,0 +1,604 @@
+#cython: language_level=3
+
+from obitools3.apps.progress cimport ProgressBar  # @UnresolvedImport
+from obitools3.dms import DMS
+from obitools3.dms.view import RollbackException
+from obitools3.dms.view.typed_view.view_NUC_SEQS cimport View_NUC_SEQS
+from obitools3.dms.column.column cimport Column, Column_line
+from obitools3.apps.optiongroups import addMinimalInputOption, addMinimalOutputOption
+from obitools3.uri.decode import open_uri
+from obitools3.apps.config import logger
+from obitools3.libalign._freeendgapfm import FreeEndGapFullMatch
+from obitools3.libalign.apat_pattern import Primer_search
+from obitools3.dms.obiseq cimport Nuc_Seq
+from obitools3.dms.capi.obitypes cimport OBI_SEQ, OBI_QUAL
+from obitools3.dms.capi.apat cimport MAX_PATTERN
+from obitools3.utils cimport tobytes
+
+from libc.stdint cimport INT32_MAX
+from functools import reduce
+import math
+import sys
+
+
+REVERSE_SEQ_COLUMN_NAME = b"REVERSE_SEQUENCE"      # used by alignpairedend tool
+REVERSE_QUALITY_COLUMN_NAME = b"REVERSE_QUALITY"   # used by alignpairedend tool
+
+
+__title__="Assigns sequence records to the corresponding experiment/sample based on DNA tags and primers"
+
+
+def addOptions(parser):
+
+    addMinimalInputOption(parser)
+    addMinimalOutputOption(parser)
+ 
+    group = parser.add_argument_group('obi ngsfilter specific options')
+
+    group.add_argument('-t','--info-view',
+                     action="store", dest="ngsfilter:info_view",
+                     metavar="<URI>",
+                     type=str,
+                     default=None,
+                     help="URI to the view containing the samples definition (with tags, primers, sample names,...)")
+
+    group.add_argument('-R', '--reverse-reads',
+                     action="store", dest="ngsfilter:reverse",
+                     metavar="<URI>",
+                     default=None,
+                     type=str,
+                     help="URI to the reverse reads if the paired-end reads haven't been aligned yet")
+
+    group.add_argument('-u','--unidentified',
+                     action="store", dest="ngsfilter:unidentified",
+                     metavar="<URI>",
+                     type=str,
+                     default=None,
+                     help="URI to the view used to store the sequences unassigned to any sample")
+    
+    group.add_argument('-e','--error',
+                     action="store", dest="ngsfilter:error",
+                     metavar="###",
+                     type=int,
+                     default=2,
+                     help="Number of errors allowed for matching primers [default = 2]")
+
+
+class Primer:
+    
+    collection={}
+    
+    def __init__(self, sequence, taglength, forward=True, max_errors=2, verbose=False, primer_pair_idx=0, primer_idx=0):
+        '''
+            
+        @param sequence:
+        @type sequence:
+        @param direct:
+        @type direct:
+        '''
+        
+        assert sequence not in Primer.collection        \
+            or Primer.collection[sequence]==taglength,  \
+            "Primer %s must always be used with tags of the same length" % sequence
+            
+        Primer.collection[sequence]=taglength
+        
+        self.primer_pair_idx = primer_pair_idx
+        self.primer_idx = primer_idx
+        self.is_revcomp = False
+        self.revcomp = None
+        self.raw=sequence
+        self.sequence = Nuc_Seq(b"primer", sequence)        
+        self.lseq = len(self.sequence)
+        self.max_errors=max_errors
+        self.taglength=taglength
+        self.forward = forward
+        self.verbose=verbose
+        
+    def reverse_complement(self):
+        p = Primer(self.raw,
+                   self.taglength,
+                   not self.forward,
+                   verbose=self.verbose,
+                   max_errors=self.max_errors,
+                   primer_pair_idx=self.primer_pair_idx,
+                   primer_idx=self.primer_idx)
+        p.sequence=p.sequence.reverse_complement
+        p.is_revcomp = True
+        p.revcomp = None
+        return p
+    
+    def __hash__(self):
+        return hash(str(self.raw))
+    
+    def __eq__(self,primer):
+        return self.raw==primer.raw 
+    
+    def __call__(self, sequence, same_sequence=False, pattern=0, begin=0):
+        
+        if len(sequence) <= self.lseq:
+            return None
+                
+        ali = self.aligner.search_one_primer(sequence.seq, 
+                                             self.primer_pair_idx, 
+                                             self.primer_idx, 
+                                             reverse_comp=self.is_revcomp, 
+                                             same_sequence=same_sequence,
+                                             pattern_ref=pattern,
+                                             begin=begin)
+        
+        if ali is None:  # no match
+            return None 
+            
+        errors, start = ali.first_encountered()
+                
+        if errors <= self.max_errors:
+            end = start + self.lseq
+            if self.taglength is not None:
+                if self.sequence.is_revcomp:
+                    if (len(sequence)-end) >= self.taglength:
+                        tag_start = len(sequence) - end - self.taglength
+                        tag = sequence.reverse_complement[tag_start:tag_start+self.taglength].seq
+                    else:
+                        tag=None
+                else:
+                    if start >= self.taglength:
+                        tag = tobytes((sequence[start - self.taglength:start].seq).lower())  # turn back to lowercase because apat turned to uppercase
+                    else:
+                        tag=None
+            else:
+                tag=None
+            
+            return errors,start,end,tag
+
+        return None 
+    
+    
+    def __str__(self):
+        return "%s: %s" % ({True:'D',False:'R'}[self.forward],self.raw)
+    
+    __repr__=__str__
+
+
+cdef read_info_view(info_view, max_errors=2, verbose=False, not_aligned=False):
+    infos = {}
+    primer_list = []
+    i=0
+    for p in info_view:
+        forward=Primer(p[b'forward_primer'],
+                       len(p[b'forward_tag']) if p[b'forward_tag']!=b'-' else None,
+                       True,
+                       max_errors=max_errors,
+                       verbose=verbose,
+                       primer_pair_idx=i,
+                       primer_idx=0)
+        
+        fp = infos.get(forward,{})
+        infos[forward]=fp
+        
+        reverse=Primer(p[b'reverse_primer'],
+                       len(p[b'reverse_tag']) if p[b'reverse_tag']!=b'-' else None,
+                       False,
+                       max_errors=max_errors,
+                       verbose=verbose,
+                       primer_pair_idx=i,
+                       primer_idx=1)
+
+        primer_list.append((p[b'forward_primer'], p[b'reverse_primer']))
+        
+        rp = infos.get(reverse,{})
+        infos[reverse]=rp
+        
+        if not_aligned:
+            cf=forward
+            cr=reverse
+            
+            cf.revcomp = forward.reverse_complement()
+            cr.revcomp = reverse.reverse_complement()
+
+            dpp=fp.get(cr,{})
+            fp[cr]=dpp
+            
+            rpp=rp.get(cf,{})
+            rp[cf]=rpp
+        
+        else:
+            cf=forward.reverse_complement()
+            cr=reverse.reverse_complement()
+            
+            dpp=fp.get(cr,{})
+            fp[cr]=dpp
+             
+            rpp=rp.get(cf,{})
+            rp[cf]=rpp
+
+        tags = (p[b'forward_tag'] if p[b'forward_tag']!=b'-' else None,
+                p[b'reverse_tag'] if p[b'reverse_tag']!=b'-' else None)
+        
+        assert tags not in dpp, \
+               "Tag pair %s is already used with primer pairs: (%s,%s)" % (str(tags),forward,reverse)
+        
+        # Save additional data
+        special_keys = [b'forward_primer', b'reverse_primer', b'forward_tag', b'reverse_tag']
+        data={}
+        for key in p:
+            if key not in special_keys:
+                data[key] = p[key]
+                            
+        dpp[tags] = data
+        rpp[tags] = data
+        
+        i+=1
+        
+    return infos, primer_list
+    
+
+cdef tuple annotate(sequences, infos, verbose=False):
+        
+    def sortMatch(match):
+        if match[1] is None:
+            return INT32_MAX
+        else:
+            return match[1][1]
+
+    def sortReverseMatch(match):
+        if match[1] is None:
+            return -1
+        else:
+            return match[1][1]
+    
+    not_aligned = len(sequences) > 1
+    sequenceF = sequences[0]
+    sequenceR = None
+    if not not_aligned: 
+        final_sequence = sequenceF
+    else:
+        final_sequence = sequenceF.clone()   # TODO maybe not cloning and then deleting quality tags is more efficient
+
+    if not_aligned:
+        sequenceR = sequences[1]
+        final_sequence[REVERSE_SEQ_COLUMN_NAME] = sequenceR.seq             # used by alignpairedend tool
+        final_sequence[REVERSE_QUALITY_COLUMN_NAME] = sequenceR.quality     # used by alignpairedend tool
+
+    for seq in sequences:
+        if hasattr(seq, "quality_array"): 
+            q = -reduce(lambda x,y:x+y,(math.log10(z) for z in seq.quality_array),0)/len(seq.quality_array)*10
+            seq[b'avg_quality']=q
+            q = -reduce(lambda x,y:x+y,(math.log10(z) for z in seq.quality_array[0:10]),0)
+            seq[b'head_quality']=q
+            if len(seq.quality_array[10:-10]) :
+                q = -reduce(lambda x,y:x+y,(math.log10(z) for z in seq.quality_array[10:-10]),0)/len(seq.quality_array[10:-10])*10
+                seq[b'mid_quality']=q
+            q = -reduce(lambda x,y:x+y,(math.log10(z) for z in seq.quality_array[-10:]),0)
+            seq[b'tail_quality']=q
+    
+    # Try direct matching:
+    directmatch = []
+    first_matched_seq = None
+    second_matched_seq = None
+    for seq in sequences:
+        new_seq = True
+        pattern = 0
+        for p in infos:
+            if pattern == MAX_PATTERN:
+                new_seq = True
+                pattern = 0
+            directmatch.append((p, p(seq, same_sequence=not new_seq, pattern=pattern), seq))
+            new_seq = False
+            pattern+=1
+    
+    # Choose match closer to the start of (one of the) sequence(s)
+    directmatch = sorted(directmatch, key=sortMatch)
+    all_direct_matches = directmatch
+    directmatch = directmatch[0] if directmatch[0][1] is not None else None
+
+    if directmatch is None:
+        final_sequence[b'error']=b'No primer match'
+        return False, final_sequence
+
+    first_matched_seq = directmatch[2]
+    if id(first_matched_seq) == id(sequenceF) and not_aligned:
+        second_matched_seq = sequenceR
+    else:
+        second_matched_seq = sequenceF
+   
+    match = first_matched_seq[directmatch[1][1]:directmatch[1][2]]
+    
+    if not not_aligned:
+        final_sequence[b'seq_length_ori']=len(final_sequence)
+    
+    if not not_aligned or id(first_matched_seq) == id(sequenceF):
+        final_sequence = final_sequence[directmatch[1][2]:]
+    else:
+        cut_seq = sequenceR[directmatch[1][2]:]
+        final_sequence[REVERSE_SEQ_COLUMN_NAME] = cut_seq.seq           # used by alignpairedend tool
+        final_sequence[REVERSE_QUALITY_COLUMN_NAME] = cut_seq.quality   # used by alignpairedend tool
+    
+    if directmatch[0].forward:
+        final_sequence[b'direction']=b'forward'
+        final_sequence[b'forward_errors']=directmatch[1][0]
+        final_sequence[b'forward_primer']=directmatch[0].raw
+        final_sequence[b'forward_match']=match.seq
+        
+    else:
+        final_sequence[b'direction']=b'reverse'
+        final_sequence[b'reverse_errors']=directmatch[1][0]
+        final_sequence[b'reverse_primer']=directmatch[0].raw
+        final_sequence[b'reverse_match']=match.seq
+
+    # Keep only paired reverse primer
+    infos = infos[directmatch[0]]    
+    
+    # If not aligned, look for other match in already computed match (choose the one that makes the biggest amplicon)
+    if not_aligned:
+        i=1
+        while all_direct_matches[i][1] is None and all_direct_matches[i][0].forward and i<len(all_direct_matches):
+            i+=1
+        if i < len(all_direct_matches):
+            reversematch = all_direct_matches[i]
+        else:
+            reversematch = None
+    
+    # Look for other primer in the other direction on the sequence, or
+    # If sequences are not already aligned and reverse primer not found in most likely sequence (the one without the forward primer), try matching on the same sequence than the first match (primer in the other direction)
+    if not not_aligned or (not_aligned and reversematch[1] is None):
+        if not not_aligned:
+            sequence_to_match = second_matched_seq
+        else:
+            sequence_to_match = first_matched_seq
+        reversematch = []
+        # Compute begin
+        begin=directmatch[1][2]+1  # end of match + 1 on the same sequence
+        # Try reverse matching on the other sequence:
+        new_seq = True
+        pattern = 0
+        for p in infos:
+            if pattern == MAX_PATTERN:
+                new_seq = True
+                pattern = 0
+            if not_aligned:
+                primer=p.revcomp
+            else:
+                primer=p
+            reversematch.append((primer, primer(sequence_to_match, same_sequence=not new_seq, pattern=pattern, begin=begin)))
+            new_seq = False
+            pattern+=1
+        # Choose match closer to the end of the sequence
+        reversematch = sorted(reversematch, key=sortReverseMatch, reverse=True)
+        all_reverse_matches = reversematch
+        reversematch = reversematch[0] if reversematch[0][1] is not None else None
+        
+    if reversematch is None and None not in infos:
+        if directmatch[0].forward:
+            message = b'No reverse primer match'
+        else:
+            message = b'No direct primer match'
+        final_sequence[b'error']=message
+        return False, final_sequence
+    
+    if reversematch is None:
+        final_sequence[b'status']=b'partial'
+        
+        if directmatch[0].forward:
+            tags=(directmatch[1][3],None)
+        else:
+            tags=(None,directmatch[1][3])
+            
+        samples = infos[None]
+        
+    else:
+        final_sequence[b'status']=b'full'
+        
+        match = second_matched_seq[reversematch[1][1]:reversematch[1][2]]
+        match = match.reverse_complement
+        
+        if not not_aligned or id(second_matched_seq) == id(sequenceF):
+            final_sequence = final_sequence[0:reversematch[1][1]]
+        else:
+            cut_seq = sequenceR[reversematch[1][2]:]
+            final_sequence[REVERSE_SEQ_COLUMN_NAME] = cut_seq.seq           # used by alignpairedend tool
+            final_sequence[REVERSE_QUALITY_COLUMN_NAME] = cut_seq.quality   # used by alignpairedend tool
+        
+        if directmatch[0].forward:
+            tags=(directmatch[1][3], reversematch[1][3])
+            final_sequence[b'reverse_errors'] = reversematch[1][0]
+            final_sequence[b'reverse_primer'] = reversematch[0].raw
+            final_sequence[b'reverse_match'] = match.seq
+        
+        else:
+            tags=(reversematch[1][3], directmatch[1][3])
+            final_sequence[b'forward_errors'] = reversematch[1][0]
+            final_sequence[b'forward_primer'] = reversematch[0].raw
+            final_sequence[b'forward_match'] = match.seq
+                
+        if tags[0] is not None:
+            final_sequence[b'forward_tag'] = tags[0]
+        if tags[1] is not None:
+            final_sequence[b'reverse_tag'] = tags[1]
+
+        samples = infos[reversematch[0]]
+        
+    if not directmatch[0].forward and not not_aligned:   # don't reverse complement if not_aligned
+        final_sequence = final_sequence.reverse_complement
+
+    sample=None
+
+    if tags[0] is not None:                                    # Direct  tag known
+        if tags[1] is not None:                                # Reverse tag known
+            sample = samples.get(tags, None)             
+        else:                                                   # Only direct tag known
+            s=[samples[x] for x in samples if x[0]==tags[0]]
+            if len(s)==1:
+                sample=s[0]
+            elif len(s)>1:
+                final_sequence[b'error']=b'multiple samples match tags'
+                return False, final_sequence
+            else:
+                sample=None
+    else: 
+        if tags[1] is not None:                                 # Only reverse tag known
+            s=[samples[x] for x in samples if x[1]==tags[1]]
+            if len(s)==1:
+                sample=s[0]
+            elif len(s)>1:
+                final_sequence[b'error']=b'multiple samples match tags'
+                return False, final_sequence
+            else:
+                sample=None
+    
+    if sample is None:
+        final_sequence[b'error']=b"Cannot assign sequence to a sample"
+        return False, final_sequence
+    
+    final_sequence.update(sample)
+    
+    if not not_aligned:
+        final_sequence[b'seq_length']=len(final_sequence)
+    
+    return True, final_sequence
+
+
+def run(config):
+        
+    DMS.obi_atexit()
+    
+    logger("info", "obi ngsfilter")
+
+    assert config['ngsfilter']['info_view'] is not None, "Option -t must be specified"
+
+    # Open the input
+    
+    forward = None
+    reverse = None
+    input = None
+    not_aligned = False
+    
+    input = open_uri(config['obi']['inputURI'])
+    if input is None:
+        raise Exception("Could not open input reads")
+    if input[2] != View_NUC_SEQS:
+        raise NotImplementedError('obi ngsfilter only works on NUC_SEQS views')
+
+    if "reverse" in config["ngsfilter"]:
+        
+        forward = input[1]        
+        
+        rinput = open_uri(config["ngsfilter"]["reverse"])
+        if rinput is None:
+            raise Exception("Could not open reverse reads")
+        if rinput[2] != View_NUC_SEQS:
+            raise NotImplementedError('obi ngsfilter only works on NUC_SEQS views')
+        
+        reverse = rinput[1]
+    
+        if len(forward) != len(reverse):
+            raise Exception("Error: the number of forward and reverse reads are different")
+        
+        entries = [forward, reverse]
+        not_aligned = True
+
+        input_dms_name = [forward.dms.name, reverse.dms.name]
+        input_view_name = [forward.name, reverse.name]
+    
+    else:
+        entries = input[1]
+        input_dms_name = [entries.dms.name]
+        input_view_name = [entries.name]
+
+    
+    if not_aligned:
+        entries_len = len(forward)
+    else:
+        entries_len = len(entries)
+    
+    # Open the output
+    output = open_uri(config['obi']['outputURI'],
+                      input=False,
+                      newviewtype=View_NUC_SEQS)
+    
+    if output is None:
+        raise Exception("Could not create output view")
+    
+    o_view = output[1]
+    
+    # Open the view containing the informations about the tags and the primers
+    info_input = open_uri(config['ngsfilter']['info_view'])
+    if info_input is None:
+        raise Exception("Could not read the view containing the informations about the tags and the primers")
+    info_view = info_input[1]
+    input_dms_name.append(info_input[0].name)   
+    input_view_name.append(info_input[1].name)
+
+    # Open the unidentified view
+    if 'unidentified' in config['ngsfilter'] and config['ngsfilter']['unidentified'] is not None:  # TODO keyError if undefined problem
+        unidentified_input = open_uri(config['ngsfilter']['unidentified'],
+                                      input=False,
+                                      newviewtype=View_NUC_SEQS)
+        if unidentified_input is None:
+            raise Exception("Could not open the view containing the unidentified reads")
+        unidentified = unidentified_input[1]
+    else:
+        unidentified = None
+        
+    # Initialize the progress bar
+    pb = ProgressBar(entries_len, config, seconde=5)
+
+    # Check and store primers and tags
+    infos, primer_list = read_info_view(info_view, max_errors=config['ngsfilter']['error'], verbose=False, not_aligned=not_aligned)   # TODO obi verbose option
+    
+    aligner = Primer_search(primer_list, config['ngsfilter']['error'])
+    
+    for p in infos:
+        p.aligner = aligner
+        for paired_p in infos[p]:
+            paired_p.aligner = aligner
+            if paired_p.revcomp is not None:
+                paired_p.revcomp.aligner = aligner
+    
+    if not_aligned:   # create columns used by alignpairedend tool
+        Column.new_column(o_view, REVERSE_SEQ_COLUMN_NAME, OBI_SEQ)
+        Column.new_column(o_view, REVERSE_QUALITY_COLUMN_NAME, OBI_QUAL, associated_column_name=REVERSE_SEQ_COLUMN_NAME, associated_column_version=o_view[REVERSE_SEQ_COLUMN_NAME].version)
+        
+        Column.new_column(unidentified, REVERSE_SEQ_COLUMN_NAME, OBI_SEQ)
+        Column.new_column(unidentified, REVERSE_QUALITY_COLUMN_NAME, OBI_QUAL, associated_column_name=REVERSE_SEQ_COLUMN_NAME, associated_column_version=unidentified[REVERSE_SEQ_COLUMN_NAME].version)
+    
+    g = 0
+    u = 0
+    try:
+        for i in range(entries_len):
+            pb(i)
+            if not_aligned:
+                modseq = [Nuc_Seq.new_from_stored(forward[i]), Nuc_Seq.new_from_stored(reverse[i])]
+            else:
+                modseq = [Nuc_Seq.new_from_stored(entries[i])]
+            good, oseq = annotate(modseq, infos)
+            if good:
+                o_view[g].set(oseq.id, oseq.seq, definition=oseq.definition, quality=oseq.quality, tags=oseq)
+                g+=1
+            elif unidentified is not None:
+                unidentified[u].set(oseq.id, oseq.seq, definition=oseq.definition, quality=oseq.quality, tags=oseq)
+                u+=1
+    except Exception, e:
+        raise RollbackException("obi ngsfilter error, rollbacking views: "+str(e), o_view, unidentified)
+    
+    pb(i, force=True)
+    print("", file=sys.stderr)
+
+    # Save command config in View and DMS comments
+    command_line = " ".join(sys.argv[1:])
+    o_view.write_config(config, "ngsfilter", command_line, input_dms_name=input_dms_name, input_view_name=input_view_name)
+    unidentified.write_config(config, "ngsfilter", command_line, input_dms_name=input_dms_name, input_view_name=input_view_name)
+    # Add comment about unidentified seqs
+    unidentified.comments["info"] = "View containing sequences categorized as unidentified by the ngsfilter command"
+    output[0].record_command_line(command_line)
+    
+    #print("\n\nOutput view:\n````````````", file=sys.stderr)
+    #print(repr(o_view), file=sys.stderr)
+
+    input[0].close()
+    output[0].close()
+    info_input[0].close()
+    unidentified_input[0].close()
+    aligner.free()
+
+    logger("info", "Done.")

python/obitools3/commands/sort.cfiles

@@ -0,0 +1,103 @@
+../../../src/obi_lcs.h
+../../../src/obi_lcs.c
+../../../src/obierrno.h
+../../../src/obierrno.c
+../../../src/upperband.h
+../../../src/upperband.c
+../../../src/sse_banded_LCS_alignment.h
+../../../src/sse_banded_LCS_alignment.c
+../../../src/obiblob.h
+../../../src/obiblob.c
+../../../src/utils.h
+../../../src/utils.c
+../../../src/obidms.h
+../../../src/obidms.c
+../../../src/libjson/json_utils.h
+../../../src/libjson/json_utils.c
+../../../src/libjson/cJSON.h
+../../../src/libjson/cJSON.c
+../../../src/obiavl.h
+../../../src/obiavl.c
+../../../src/bloom.h
+../../../src/bloom.c
+../../../src/crc64.h
+../../../src/crc64.c
+../../../src/murmurhash2.h
+../../../src/murmurhash2.c
+../../../src/obidmscolumn.h
+../../../src/obidmscolumn.c
+../../../src/obitypes.h
+../../../src/obitypes.c
+../../../src/obidmscolumndir.h
+../../../src/obidmscolumndir.c
+../../../src/obiblob_indexer.h
+../../../src/obiblob_indexer.c
+../../../src/obiview.h
+../../../src/obiview.c
+../../../src/hashtable.h
+../../../src/hashtable.c
+../../../src/linked_list.h
+../../../src/linked_list.c
+../../../src/obidmscolumn_array.h
+../../../src/obidmscolumn_array.c
+../../../src/obidmscolumn_blob.h
+../../../src/obidmscolumn_blob.c
+../../../src/obidmscolumn_idx.h
+../../../src/obidmscolumn_idx.c
+../../../src/obidmscolumn_bool.h
+../../../src/obidmscolumn_bool.c
+../../../src/obidmscolumn_char.h
+../../../src/obidmscolumn_char.c
+../../../src/obidmscolumn_float.h
+../../../src/obidmscolumn_float.c
+../../../src/obidmscolumn_int.h
+../../../src/obidmscolumn_int.c
+../../../src/obidmscolumn_qual.h
+../../../src/obidmscolumn_qual.c
+../../../src/obidmscolumn_seq.h
+../../../src/obidmscolumn_seq.c
+../../../src/obidmscolumn_str.h
+../../../src/obidmscolumn_str.c
+../../../src/array_indexer.h
+../../../src/array_indexer.c
+../../../src/char_str_indexer.h
+../../../src/char_str_indexer.c
+../../../src/dna_seq_indexer.h
+../../../src/dna_seq_indexer.c
+../../../src/encode.c
+../../../src/encode.h
+../../../src/uint8_indexer.c
+../../../src/uint8_indexer.h
+../../../src/build_reference_db.c
+../../../src/build_reference_db.h
+../../../src/kmer_similarity.c
+../../../src/kmer_similarity.h
+../../../src/obi_clean.c
+../../../src/obi_clean.h
+../../../src/obi_ecopcr.c
+../../../src/obi_ecopcr.h
+../../../src/obi_ecotag.c
+../../../src/obi_ecotag.h
+../../../src/obidms_taxonomy.c
+../../../src/obidms_taxonomy.h
+../../../src/obilittlebigman.c
+../../../src/obilittlebigman.h
+../../../src/_sse.h
+../../../src/obidebug.h
+../../../src/libecoPCR/libapat/CODES/dft_code.h
+../../../src/libecoPCR/libapat/CODES/dna_code.h
+../../../src/libecoPCR/libapat/CODES/prot_code.h
+../../../src/libecoPCR/libapat/apat_parse.c
+../../../src/libecoPCR/libapat/apat_search.c
+../../../src/libecoPCR/libapat/apat.h
+../../../src/libecoPCR/libapat/Gmach.h
+../../../src/libecoPCR/libapat/Gtypes.h
+../../../src/libecoPCR/libapat/libstki.c
+../../../src/libecoPCR/libapat/libstki.h
+../../../src/libecoPCR/libthermo/nnparams.h
+../../../src/libecoPCR/libthermo/nnparams.c
+../../../src/libecoPCR/ecoapat.c
+../../../src/libecoPCR/ecodna.c
+../../../src/libecoPCR/ecoError.c
+../../../src/libecoPCR/ecoMalloc.c
+../../../src/libecoPCR/ecoPCR.h

python/obitools3/commands/sort.pyx

@@ -0,0 +1,144 @@
+#cython: language_level=3
+
+from obitools3.apps.progress cimport ProgressBar  # @UnresolvedImport
+from obitools3.dms import DMS
+from obitools3.dms.view.view cimport View, Line_selection
+from obitools3.uri.decode import open_uri
+from obitools3.apps.optiongroups import addMinimalInputOption, addMinimalOutputOption
+from obitools3.dms.view import RollbackException
+from obitools3.apps.config import logger
+from obitools3.utils cimport str2bytes
+
+from obitools3.dms.capi.obitypes cimport OBI_BOOL, \
+                                         OBI_CHAR, \
+                                         OBI_FLOAT, \
+                                         OBI_INT, \
+                                         OBI_QUAL, \
+                                         OBI_SEQ, \
+                                         OBI_STR, \
+                                         OBIBool_NA, \
+                                         OBIChar_NA, \
+                                         OBIFloat_NA, \
+                                         OBIInt_NA
+
+import time
+import sys
+
+ 
+NULL_VALUE = {OBI_BOOL: OBIBool_NA, 
+              OBI_CHAR: OBIChar_NA, 
+              OBI_FLOAT: OBIFloat_NA,
+              OBI_INT: OBIInt_NA,
+              OBI_QUAL: [],
+              OBI_SEQ: b"",
+              OBI_STR: b""}
+ 
+
+__title__="Sort view lines according to the value of a given attribute."
+
+ 
+def addOptions(parser):
+    
+    addMinimalInputOption(parser)
+    addMinimalOutputOption(parser)
+
+    group=parser.add_argument_group('obi sort specific options')
+
+    group.add_argument('--key', '-k',
+                       action="append", dest="sort:keys",
+                       metavar='<TAG NAME>',
+                       default=[],
+                       type=str,
+                       help="Attribute used to sort the sequence records.")
+
+    group.add_argument('--reverse', '-r',
+                       action="store_true", dest="sort:reverse",
+                       default=False,
+                       help="Sort in reverse order.")
+
+
+def line_cmp(line, key, pb): 
+    pb   
+    if line[key] is None:
+        return NULL_VALUE[line.view[key].data_type_int]
+    else:
+        return line[key]
+
+     
+def run(config):
+     
+    DMS.obi_atexit()
+    
+    logger("info", "obi sort")
+
+    # Open the input
+    input = open_uri(config["obi"]["inputURI"])
+    if input is None:
+        raise Exception("Could not read input view")
+    i_dms = input[0]
+    i_view = input[1]
+
+    # Open the output: only the DMS
+    output = open_uri(config['obi']['outputURI'],
+                      input=False,
+                      dms_only=True)
+    if output is None:
+        raise Exception("Could not create output view")
+    o_dms = output[0]
+    o_view_name_final = output[1]
+    o_view_name = o_view_name_final
+    
+    # If the input and output DMS are not the same, create output view in input DMS first, then export it
+    # to output DMS, making sure the temporary view name is unique in the input DMS 
+    if i_dms != o_dms:
+        i=0
+        while o_view_name in i_dms:
+            o_view_name = o_view_name_final+b"_"+str2bytes(str(i))
+            i+=1        
+
+    # Initialize the progress bar
+    pb = ProgressBar(len(i_view), config, seconde=5)
+    
+    keys = config['sort']['keys']
+        
+    selection = Line_selection(i_view)
+    
+    for i in range(len(i_view)):  # TODO special function?
+        selection.append(i)
+    
+    for k in keys:  # TODO order?
+        selection.sort(key=lambda line_idx: line_cmp(i_view[line_idx], k, pb(line_idx)), reverse=config['sort']['reverse'])
+
+    pb(len(i_view), force=True)
+    print("", file=sys.stderr)
+
+    # Create output view with the sorted line selection
+    try:
+        o_view = selection.materialize(o_view_name)
+    except Exception, e:
+        raise RollbackException("obi sort error, rollbacking view: "+str(e), o_view)
+
+    # Save command config in View and DMS comments
+    command_line = " ".join(sys.argv[1:])
+    input_dms_name=[input[0].name]
+    input_view_name=[input[1].name]
+    o_view.write_config(config, "sort", command_line, input_dms_name=input_dms_name, input_view_name=input_view_name)
+    o_dms.record_command_line(command_line)
+
+    # If input and output DMS are not the same, export the temporary view to the output DMS
+    # and delete the temporary view in the input DMS
+    if i_dms != o_dms:
+        o_view.close()
+        View.import_view(i_dms.full_path[:-7], o_dms.full_path[:-7], o_view_name, o_view_name_final)
+        o_view = o_dms[o_view_name_final]
+
+    #print("\n\nOutput view:\n````````````", file=sys.stderr)
+    #print(repr(o_view), file=sys.stderr)
+
+    # If the input and the output DMS are different, delete the temporary imported view used to create the final view
+    if i_dms != o_dms:
+        View.delete_view(i_dms, o_view_name)
+        o_dms.close()
+    i_dms.close()
+
+    logger("info", "Done.")

python/obitools3/commands/stats.cfiles

@@ -0,0 +1,103 @@
+../../../src/obi_lcs.h
+../../../src/obi_lcs.c
+../../../src/obierrno.h
+../../../src/obierrno.c
+../../../src/upperband.h
+../../../src/upperband.c
+../../../src/sse_banded_LCS_alignment.h
+../../../src/sse_banded_LCS_alignment.c
+../../../src/obiblob.h
+../../../src/obiblob.c
+../../../src/utils.h
+../../../src/utils.c
+../../../src/obidms.h
+../../../src/obidms.c
+../../../src/libjson/json_utils.h
+../../../src/libjson/json_utils.c
+../../../src/libjson/cJSON.h
+../../../src/libjson/cJSON.c
+../../../src/obiavl.h
+../../../src/obiavl.c
+../../../src/bloom.h
+../../../src/bloom.c
+../../../src/crc64.h
+../../../src/crc64.c
+../../../src/murmurhash2.h
+../../../src/murmurhash2.c
+../../../src/obidmscolumn.h
+../../../src/obidmscolumn.c
+../../../src/obitypes.h
+../../../src/obitypes.c
+../../../src/obidmscolumndir.h
+../../../src/obidmscolumndir.c
+../../../src/obiblob_indexer.h
+../../../src/obiblob_indexer.c
+../../../src/obiview.h
+../../../src/obiview.c
+../../../src/hashtable.h
+../../../src/hashtable.c
+../../../src/linked_list.h
+../../../src/linked_list.c
+../../../src/obidmscolumn_array.h
+../../../src/obidmscolumn_array.c
+../../../src/obidmscolumn_blob.h
+../../../src/obidmscolumn_blob.c
+../../../src/obidmscolumn_idx.h
+../../../src/obidmscolumn_idx.c
+../../../src/obidmscolumn_bool.h
+../../../src/obidmscolumn_bool.c
+../../../src/obidmscolumn_char.h
+../../../src/obidmscolumn_char.c
+../../../src/obidmscolumn_float.h
+../../../src/obidmscolumn_float.c
+../../../src/obidmscolumn_int.h
+../../../src/obidmscolumn_int.c
+../../../src/obidmscolumn_qual.h
+../../../src/obidmscolumn_qual.c
+../../../src/obidmscolumn_seq.h
+../../../src/obidmscolumn_seq.c
+../../../src/obidmscolumn_str.h
+../../../src/obidmscolumn_str.c
+../../../src/array_indexer.h
+../../../src/array_indexer.c
+../../../src/char_str_indexer.h
+../../../src/char_str_indexer.c
+../../../src/dna_seq_indexer.h
+../../../src/dna_seq_indexer.c
+../../../src/encode.c
+../../../src/encode.h
+../../../src/uint8_indexer.c
+../../../src/uint8_indexer.h
+../../../src/build_reference_db.c
+../../../src/build_reference_db.h
+../../../src/kmer_similarity.c
+../../../src/kmer_similarity.h
+../../../src/obi_clean.c
+../../../src/obi_clean.h
+../../../src/obi_ecopcr.c
+../../../src/obi_ecopcr.h
+../../../src/obi_ecotag.c
+../../../src/obi_ecotag.h
+../../../src/obidms_taxonomy.c
+../../../src/obidms_taxonomy.h
+../../../src/obilittlebigman.c
+../../../src/obilittlebigman.h
+../../../src/_sse.h
+../../../src/obidebug.h
+../../../src/libecoPCR/libapat/CODES/dft_code.h
+../../../src/libecoPCR/libapat/CODES/dna_code.h
+../../../src/libecoPCR/libapat/CODES/prot_code.h
+../../../src/libecoPCR/libapat/apat_parse.c
+../../../src/libecoPCR/libapat/apat_search.c
+../../../src/libecoPCR/libapat/apat.h
+../../../src/libecoPCR/libapat/Gmach.h
+../../../src/libecoPCR/libapat/Gtypes.h
+../../../src/libecoPCR/libapat/libstki.c
+../../../src/libecoPCR/libapat/libstki.h
+../../../src/libecoPCR/libthermo/nnparams.h
+../../../src/libecoPCR/libthermo/nnparams.c
+../../../src/libecoPCR/ecoapat.c
+../../../src/libecoPCR/ecodna.c
+../../../src/libecoPCR/ecoError.c
+../../../src/libecoPCR/ecoMalloc.c
+../../../src/libecoPCR/ecoPCR.h

python/obitools3/commands/stats.pyx

@@ -0,0 +1,265 @@
+#cython: language_level=3
+
+from obitools3.apps.progress cimport ProgressBar  # @UnresolvedImport
+from obitools3.dms import DMS
+from obitools3.uri.decode import open_uri
+from obitools3.apps.optiongroups import addMinimalInputOption, addTaxonomyOption
+from obitools3.dms.view import RollbackException
+from obitools3.apps.config import logger
+from obitools3.dms.capi.obiview cimport COUNT_COLUMN
+
+from functools import reduce
+import math
+import time
+import sys
+ 
+
+__title__="Compute basic statistics for attribute values."
+
+'''
+`obi stats` computes basic statistics for attribute values of sequence records.
+The sequence records can be categorized or not using one or several ``-c`` options.
+By default, only the number of sequence records and the total count are computed for each category. 
+Additional statistics can be computed for attribute values in each category, such as:
+
+    - minimum value (``-m`` option) 
+    - maximum value (``-M`` option) 
+    - mean value (``-a`` option) 
+    - variance (``-v`` option) 
+    - standard deviation (``-s`` option)
+    
+The result is a contingency table with the different categories in rows, and the 
+computed statistics in columns. 
+'''
+
+
+# TODO: when is the taxonomy possibly used?
+
+ 
+def addOptions(parser):
+    
+    addMinimalInputOption(parser)
+    addTaxonomyOption(parser)
+
+    group=parser.add_argument_group('obi stats specific options')
+
+    group.add_argument('-c','--category-attribute',
+                       action="append", dest="stats:categories",
+                             metavar="<Attribute Name>",
+                             default=[],
+                             help="Attribute used to categorize the records.")
+    
+    group.add_argument('-m','--min',
+                       action="append", dest="stats:minimum",
+                       metavar="<Attribute Name>",
+                       default=[],
+                       help="Compute the minimum value of attribute for each category.")
+    
+    group.add_argument('-M','--max',
+                       action="append", dest="stats:maximum",
+                       metavar="<Attribute Name>",
+                       default=[],
+                       help="Compute the maximum value of attribute for each category.")
+
+    group.add_argument('-a','--mean',
+                       action="append", dest="stats:mean",
+                       metavar="<Attribute Name>",
+                       default=[],
+                       help="Compute the mean value of attribute for each category.")
+
+    group.add_argument('-v','--variance',
+                       action="append", dest="stats:var",
+                       metavar="<Attribute Name>",
+                       default=[],
+                       help="Compute the variance of attribute for each category.")
+
+    group.add_argument('-s','--std-dev',
+                       action="append", dest="stats:sd",
+                       metavar="<Attribute Name>",
+                       default=[],
+                       help="Compute the standard deviation of attribute for each category.")
+
+
+def statistics(values, attributes, func):
+    
+    stat={}
+    lstat={}
+    
+    for var in attributes:
+        if var in values:
+            stat[var]={}
+            lstat[var]=0
+            for c in values[var]:
+                v = values[var][c]
+                m = func(v)
+                stat[var][c]=m
+                lm=len(str(m))
+                if lm > lstat[var]:
+                    lstat[var]=lm
+                
+    return stat, lstat
+
+
+def minimum(values, options):
+    return statistics(values, options['minimum'], min)
+    
+
+def maximum(values, options):
+    return statistics(values, options['maximum'], max)
+
+
+def mean(values, options):
+    def average(v):
+        s = reduce(lambda x,y:x+y,v,0)
+        return float(s)/len(v)
+    return statistics(values, options['mean'], average)
+
+
+def variance(v):
+    if len(v)==1: 
+        return 0 
+    s = reduce(lambda x,y:(x[0]+y,x[1]+y**2),v,(0.,0.))
+    return s[1]/(len(v)-1) - s[0]**2/len(v)/(len(v)-1)
+
+
+def varpop(values, options):
+    return statistics(values, options['var'], variance)
+    
+
+def sd(values, options):
+    def stddev(v):
+        return math.sqrt(variance(v))
+    return statistics(values, options['sd'], stddev)
+
+ 
+def run(config):
+     
+    DMS.obi_atexit()
+    
+    logger("info", "obi stats")
+
+    # Open the input
+    input = open_uri(config['obi']['inputURI'])
+    if input is None:
+        raise Exception("Could not read input view")
+    i_view = input[1]
+
+    if 'taxoURI' in config['obi'] and config['obi']['taxoURI'] is not None:
+        taxo_uri = open_uri(config['obi']['taxoURI'])
+        if taxo_uri is None:
+            raise Exception("Couldn't open taxonomy")
+        taxo = taxo_uri[1]
+    else :
+        taxo = None
+
+    statistics = set(config['stats']['minimum']) | set(config['stats']['maximum']) | set(config['stats']['mean'])
+    total = 0
+    catcount={}
+    totcount={}
+    values={}
+    lcat=0
+    
+    # Initialize the progress bar
+    pb = ProgressBar(len(i_view), config, seconde=5)
+    
+    for i in range(len(i_view)):
+        pb(i)
+        line = i_view[i]
+        
+        category = []
+        for c in config['stats']['categories']:
+            try:
+                if taxo is not None:
+                    loc_env = {'sequence': line, 'line': line, 'taxonomy': taxo}
+                else:
+                    loc_env = {'sequence': line, 'line': line}
+
+                v = eval(c, loc_env, line)
+                
+                lv=len(str(v))
+                if lv > lcat:
+                    lcat=lv
+                category.append(v)
+            except:
+                category.append(None)
+                if 4 > lcat:
+                    lcat=4
+
+        category=tuple(category)
+        catcount[category]=catcount.get(category,0)+1
+        try: 
+            totcount[category]=totcount.get(category,0)+line[COUNT_COLUMN]
+        except KeyError:
+            totcount[category]=totcount.get(category,0)+1
+        for var in statistics:
+            if var in line:
+                v = line[var]
+                if var not in values:
+                    values[var]={}
+                if category not in values[var]:
+                    values[var][category]=[]
+                values[var][category].append(v)    
+
+    pb(i, force=True)
+    print("", file=sys.stderr)
+    
+    mini, lmini = minimum(values, config['stats'])
+    maxi, lmaxi = maximum(values, config['stats'])
+    avg, lavg = mean(values, config['stats'])
+    varp, lvarp = varpop(values, config['stats'])
+    sigma, lsigma = sd(values, config['stats'])
+
+    pcat = "%%-%ds" % lcat
+    if config['stats']['minimum']:
+        minvar= "min_%%-%ds" % max(len(x) for x in config['stats']['minimum'])
+    else:
+        minvar= "%s"
+        
+    if config['stats']['maximum']:
+        maxvar= "max_%%-%ds" % max(len(x) for x in config['stats']['maximum'])
+    else:
+        maxvar= "%s"
+        
+    if config['stats']['mean']:
+        meanvar= "mean_%%-%ds" % max(len(x) for x in config['stats']['mean'])
+    else:
+        meanvar= "%s"
+        
+    if config['stats']['var']:
+        varvar= "var_%%-%ds" % max(len(x) for x in config['stats']['var'])
+    else:
+        varvar= "%s"
+        
+    if config['stats']['sd']:
+        sdvar= "sd_%%-%ds" % max(len(x) for x in config['stats']['sd'])
+    else:
+        sdvar= "%s"
+        
+    hcat = "\t".join([pcat % x for x in config['stats']['categories']]) + "\t" +\
+           "\t".join([minvar % x for x in config['stats']['minimum']])  + "\t" +\
+           "\t".join([maxvar % x for x in config['stats']['maximum']])  + "\t" +\
+           "\t".join([meanvar % x for x in config['stats']['mean']])  + "\t" +\
+           "\t".join([varvar % x for x in config['stats']['var']])  + "\t" +\
+           "\t".join([sdvar % x for x in config['stats']['sd']]) + \
+           "\t   count" + \
+           "\t   total" 
+    print(hcat)
+    for c in catcount:
+        for v in c:
+            print(pcat % str(v)+"\t", end="")
+        for m in config['stats']['minimum']:
+            print((("%%%dd" % lmini[m]) % mini[m][c])+"\t", end="")
+        for m in config['stats']['maximum']:
+            print((("%%%dd" % lmaxi[m]) % maxi[m][c])+"\t", end="")
+        for m in config['stats']['mean']:
+            print((("%%%df" % lavg[m]) % avg[m][c])+"\t", end="")
+        for m in config['stats']['var']:
+            print((("%%%df" % lvarp[m]) % varp[m][c])+"\t", end="")
+        for m in config['stats']['sd']:
+            print((("%%%df" % lsigma[m]) % sigma[m][c])+"\t", end="")
+        print("%7d" %catcount[c], end="")
+        print("%9d" %totcount[c])
+
+    input[0].close()
+    
+    logger("info", "Done.")

python/obitools3/commands/tail.cfiles

@@ -0,0 +1,103 @@
+../../../src/obi_lcs.h
+../../../src/obi_lcs.c
+../../../src/obierrno.h
+../../../src/obierrno.c
+../../../src/upperband.h
+../../../src/upperband.c
+../../../src/sse_banded_LCS_alignment.h
+../../../src/sse_banded_LCS_alignment.c
+../../../src/obiblob.h
+../../../src/obiblob.c
+../../../src/utils.h
+../../../src/utils.c
+../../../src/obidms.h
+../../../src/obidms.c
+../../../src/libjson/json_utils.h
+../../../src/libjson/json_utils.c
+../../../src/libjson/cJSON.h
+../../../src/libjson/cJSON.c
+../../../src/obiavl.h
+../../../src/obiavl.c
+../../../src/bloom.h
+../../../src/bloom.c
+../../../src/crc64.h
+../../../src/crc64.c
+../../../src/murmurhash2.h
+../../../src/murmurhash2.c
+../../../src/obidmscolumn.h
+../../../src/obidmscolumn.c
+../../../src/obitypes.h
+../../../src/obitypes.c
+../../../src/obidmscolumndir.h
+../../../src/obidmscolumndir.c
+../../../src/obiblob_indexer.h
+../../../src/obiblob_indexer.c
+../../../src/obiview.h
+../../../src/obiview.c
+../../../src/hashtable.h
+../../../src/hashtable.c
+../../../src/linked_list.h
+../../../src/linked_list.c
+../../../src/obidmscolumn_array.h
+../../../src/obidmscolumn_array.c
+../../../src/obidmscolumn_blob.h
+../../../src/obidmscolumn_blob.c
+../../../src/obidmscolumn_idx.h
+../../../src/obidmscolumn_idx.c
+../../../src/obidmscolumn_bool.h
+../../../src/obidmscolumn_bool.c
+../../../src/obidmscolumn_char.h
+../../../src/obidmscolumn_char.c
+../../../src/obidmscolumn_float.h
+../../../src/obidmscolumn_float.c
+../../../src/obidmscolumn_int.h
+../../../src/obidmscolumn_int.c
+../../../src/obidmscolumn_qual.h
+../../../src/obidmscolumn_qual.c
+../../../src/obidmscolumn_seq.h
+../../../src/obidmscolumn_seq.c
+../../../src/obidmscolumn_str.h
+../../../src/obidmscolumn_str.c
+../../../src/array_indexer.h
+../../../src/array_indexer.c
+../../../src/char_str_indexer.h
+../../../src/char_str_indexer.c
+../../../src/dna_seq_indexer.h
+../../../src/dna_seq_indexer.c
+../../../src/encode.c
+../../../src/encode.h
+../../../src/uint8_indexer.c
+../../../src/uint8_indexer.h
+../../../src/build_reference_db.c
+../../../src/build_reference_db.h
+../../../src/kmer_similarity.c
+../../../src/kmer_similarity.h
+../../../src/obi_clean.c
+../../../src/obi_clean.h
+../../../src/obi_ecopcr.c
+../../../src/obi_ecopcr.h
+../../../src/obi_ecotag.c
+../../../src/obi_ecotag.h
+../../../src/obidms_taxonomy.c
+../../../src/obidms_taxonomy.h
+../../../src/obilittlebigman.c
+../../../src/obilittlebigman.h
+../../../src/_sse.h
+../../../src/obidebug.h
+../../../src/libecoPCR/libapat/CODES/dft_code.h
+../../../src/libecoPCR/libapat/CODES/dna_code.h
+../../../src/libecoPCR/libapat/CODES/prot_code.h
+../../../src/libecoPCR/libapat/apat_parse.c
+../../../src/libecoPCR/libapat/apat_search.c
+../../../src/libecoPCR/libapat/apat.h
+../../../src/libecoPCR/libapat/Gmach.h
+../../../src/libecoPCR/libapat/Gtypes.h
+../../../src/libecoPCR/libapat/libstki.c
+../../../src/libecoPCR/libapat/libstki.h
+../../../src/libecoPCR/libthermo/nnparams.h
+../../../src/libecoPCR/libthermo/nnparams.c
+../../../src/libecoPCR/ecoapat.c
+../../../src/libecoPCR/ecodna.c
+../../../src/libecoPCR/ecoError.c
+../../../src/libecoPCR/ecoMalloc.c
+../../../src/libecoPCR/ecoPCR.h

python/obitools3/commands/tail.pyx

@@ -0,0 +1,110 @@
+#cython: language_level=3
+
+from obitools3.apps.progress cimport ProgressBar  # @UnresolvedImport
+from obitools3.dms import DMS
+from obitools3.dms.view.view cimport View, Line_selection
+from obitools3.uri.decode import open_uri
+from obitools3.apps.optiongroups import addMinimalInputOption, addMinimalOutputOption
+from obitools3.dms.view import RollbackException
+from obitools3.apps.config import logger
+from obitools3.utils cimport str2bytes
+
+import time
+import sys
+
+
+__title__="Keep the N last lines of a view."
+
+ 
+def addOptions(parser):
+    
+    addMinimalInputOption(parser)
+    addMinimalOutputOption(parser)
+
+    group=parser.add_argument_group('obi tail specific options')
+
+    group.add_argument('-n', '--sequence-count',
+                       action="store", dest="tail:count",
+                       metavar='<N>',
+                       default=10,
+                       type=int,
+                       help="Number of last records to keep.")
+
+     
+def run(config):
+     
+    DMS.obi_atexit()
+    
+    logger("info", "obi tail")
+
+    # Open the input
+    input = open_uri(config["obi"]["inputURI"])
+    if input is None:
+        raise Exception("Could not read input view")
+    i_dms = input[0]
+    i_view = input[1]
+
+    # Open the output: only the DMS
+    output = open_uri(config['obi']['outputURI'],
+                      input=False,
+                      dms_only=True)
+    if output is None:
+        raise Exception("Could not create output view")
+    o_dms = output[0]
+    o_view_name_final = output[1]
+    o_view_name = o_view_name_final
+    
+    # If the input and output DMS are not the same, create output view in input DMS first, then export it
+    # to output DMS, making sure the temporary view name is unique in the input DMS 
+    if i_dms != o_dms:
+        i=0
+        while o_view_name in i_dms:
+            o_view_name = o_view_name_final+b"_"+str2bytes(str(i))
+            i+=1        
+    
+    start = max(len(i_view) - config['tail']['count'], 0)
+
+    # Initialize the progress bar
+    pb = ProgressBar(len(i_view) - start, config, seconde=5)
+        
+    selection = Line_selection(i_view)
+    
+    for i in range(start, len(i_view)):
+        pb(i)
+        selection.append(i)
+
+    pb(i, force=True)
+    print("", file=sys.stderr)
+
+    # Save command config in View comments
+    command_line = " ".join(sys.argv[1:])
+    comments = View.get_config_dict(config, "tail", command_line, input_dms_name=[i_dms.name], input_view_name=[i_view.name])
+
+    # Create output view with the line selection
+    try:
+        o_view = selection.materialize(o_view_name)
+    except Exception, e:
+        raise RollbackException("obi tail error, rollbacking view: "+str(e), o_view)
+
+    # Save command config in DMS comments
+    command_line = " ".join(sys.argv[1:])
+    o_view.write_config(config, "tail", command_line, input_dms_name=[i_dms.name], input_view_name=[i_view.name])
+    o_dms.record_command_line(command_line)
+
+    # If input and output DMS are not the same, export the temporary view to the output DMS
+    # and delete the temporary view in the input DMS
+    if i_dms != o_dms:
+        o_view.close()
+        View.import_view(i_dms.full_path[:-7], o_dms.full_path[:-7], o_view_name, o_view_name_final)
+        o_view = o_dms[o_view_name_final]
+
+    #print("\n\nOutput view:\n````````````", file=sys.stderr)
+    #print(repr(o_view), file=sys.stderr)
+
+    # If the input and the output DMS are different, delete the temporary imported view used to create the final view
+    if i_dms != o_dms:
+        View.delete_view(i_dms, o_view_name)
+        o_dms.close()
+    i_dms.close()
+    
+    logger("info", "Done.")

python/obitools3/commands/test.cfiles

@@ -0,0 +1,103 @@
+../../../src/obi_lcs.h
+../../../src/obi_lcs.c
+../../../src/obierrno.h
+../../../src/obierrno.c
+../../../src/upperband.h
+../../../src/upperband.c
+../../../src/sse_banded_LCS_alignment.h
+../../../src/sse_banded_LCS_alignment.c
+../../../src/obiblob.h
+../../../src/obiblob.c
+../../../src/utils.h
+../../../src/utils.c
+../../../src/obidms.h
+../../../src/obidms.c
+../../../src/libjson/json_utils.h
+../../../src/libjson/json_utils.c
+../../../src/libjson/cJSON.h
+../../../src/libjson/cJSON.c
+../../../src/obiavl.h
+../../../src/obiavl.c
+../../../src/bloom.h
+../../../src/bloom.c
+../../../src/crc64.h
+../../../src/crc64.c
+../../../src/murmurhash2.h
+../../../src/murmurhash2.c
+../../../src/obidmscolumn.h
+../../../src/obidmscolumn.c
+../../../src/obitypes.h
+../../../src/obitypes.c
+../../../src/obidmscolumndir.h
+../../../src/obidmscolumndir.c
+../../../src/obiblob_indexer.h
+../../../src/obiblob_indexer.c
+../../../src/obiview.h
+../../../src/obiview.c
+../../../src/hashtable.h
+../../../src/hashtable.c
+../../../src/linked_list.h
+../../../src/linked_list.c
+../../../src/obidmscolumn_array.h
+../../../src/obidmscolumn_array.c
+../../../src/obidmscolumn_blob.h
+../../../src/obidmscolumn_blob.c
+../../../src/obidmscolumn_idx.h
+../../../src/obidmscolumn_idx.c
+../../../src/obidmscolumn_bool.h
+../../../src/obidmscolumn_bool.c
+../../../src/obidmscolumn_char.h
+../../../src/obidmscolumn_char.c
+../../../src/obidmscolumn_float.h
+../../../src/obidmscolumn_float.c
+../../../src/obidmscolumn_int.h
+../../../src/obidmscolumn_int.c
+../../../src/obidmscolumn_qual.h
+../../../src/obidmscolumn_qual.c
+../../../src/obidmscolumn_seq.h
+../../../src/obidmscolumn_seq.c
+../../../src/obidmscolumn_str.h
+../../../src/obidmscolumn_str.c
+../../../src/array_indexer.h
+../../../src/array_indexer.c
+../../../src/char_str_indexer.h
+../../../src/char_str_indexer.c
+../../../src/dna_seq_indexer.h
+../../../src/dna_seq_indexer.c
+../../../src/encode.c
+../../../src/encode.h
+../../../src/uint8_indexer.c
+../../../src/uint8_indexer.h
+../../../src/build_reference_db.c
+../../../src/build_reference_db.h
+../../../src/kmer_similarity.c
+../../../src/kmer_similarity.h
+../../../src/obi_clean.c
+../../../src/obi_clean.h
+../../../src/obi_ecopcr.c
+../../../src/obi_ecopcr.h
+../../../src/obi_ecotag.c
+../../../src/obi_ecotag.h
+../../../src/obidms_taxonomy.c
+../../../src/obidms_taxonomy.h
+../../../src/obilittlebigman.c
+../../../src/obilittlebigman.h
+../../../src/_sse.h
+../../../src/obidebug.h
+../../../src/libecoPCR/libapat/CODES/dft_code.h
+../../../src/libecoPCR/libapat/CODES/dna_code.h
+../../../src/libecoPCR/libapat/CODES/prot_code.h
+../../../src/libecoPCR/libapat/apat_parse.c
+../../../src/libecoPCR/libapat/apat_search.c
+../../../src/libecoPCR/libapat/apat.h
+../../../src/libecoPCR/libapat/Gmach.h
+../../../src/libecoPCR/libapat/Gtypes.h
+../../../src/libecoPCR/libapat/libstki.c
+../../../src/libecoPCR/libapat/libstki.h
+../../../src/libecoPCR/libthermo/nnparams.h
+../../../src/libecoPCR/libthermo/nnparams.c
+../../../src/libecoPCR/ecoapat.c
+../../../src/libecoPCR/ecodna.c
+../../../src/libecoPCR/ecoError.c
+../../../src/libecoPCR/ecoMalloc.c
+../../../src/libecoPCR/ecoPCR.h

python/obitools3/commands/test.pyx

@@ -0,0 +1,531 @@
+#cython: language_level=3
+
+from obitools3.apps.progress cimport ProgressBar  # TODO I absolutely don't understand why it doesn't work without that line
+from obitools3.dms.view import View, Line_selection
+from obitools3.dms.view.typed_view.view_NUC_SEQS import View_NUC_SEQS
+from obitools3.dms import DMS
+from obitools3.dms.column import Column
+from obitools3.dms.taxo import Taxonomy
+from obitools3.utils cimport str2bytes
+from obitools3.dms.capi.obitypes cimport OBI_INT, \
+                                         OBI_FLOAT, \
+                                         OBI_BOOL, \
+                                         OBI_CHAR, \
+                                         OBI_STR, \
+                                         OBI_SEQ
+                                         
+from obitools3.dms.capi.obiview cimport NUC_SEQUENCE_COLUMN, \
+                                        ID_COLUMN, \
+                                        DEFINITION_COLUMN, \
+                                        QUALITY_COLUMN, \
+                                        COUNT_COLUMN
+
+import shutil
+import string
+import random
+
+
+VIEW_TYPES = [b"", b"NUC_SEQS_VIEW"]
+COL_TYPES = [OBI_INT, OBI_FLOAT, OBI_BOOL, OBI_CHAR, OBI_STR, OBI_SEQ]
+SPECIAL_COLUMNS = [NUC_SEQUENCE_COLUMN, ID_COLUMN, DEFINITION_COLUMN, QUALITY_COLUMN]
+
+#TAXDUMP = "" TODO path=?
+TAXTEST = b"taxtest"
+ 
+NAME_MAX_LEN = 200
+COL_COMMENTS_MAX_LEN = 2048
+MAX_INT = 2147483647    # used to generate random float values
+ 
+ 
+__title__="Tests if the obitools are working properly"
+
+
+default_config = {
+                 }
+
+
+def test_taxo(config, infos):
+    tax1 = Taxonomy.open_taxdump(infos['dms'], config['obi']['taxo'])
+    tax1.write(TAXTEST)
+    tax2 = Taxonomy.open(infos['dms'], TAXTEST)
+    assert len(tax1) == len(tax2), "Length of written taxonomy != length of read taxdump : "+str(len(tax2))+" != "+str(len(tax1))
+    
+    i = 0
+    for x in range(config['test']['nbtests']):
+        idx = random.randint(0, len(tax1)-1)
+        t1 = tax1.get_taxon_by_idx(idx)
+        taxid1 = t1.taxid
+        t2 = tax2.get_taxon_by_idx(idx)
+        taxid2 = t2.taxid
+        assert t1 == t2, "Taxon gotten from written taxonomy with index != taxon read from taxdump : "+str(t2)+" != "+str(t1)
+        t1 = tax1[taxid1]
+        t2 = tax2[taxid2]
+        assert t1 == t2, "Taxon gotten from written taxonomy with taxid != taxon read from taxdump : "+str(t2)+" != "+str(t1)
+        i+=1
+        if (i%(config['test']['nbtests']/10)) == 0 :
+            print("Testing taxonomy functions......"+str(i*100/config['test']['nbtests'])+"%")
+
+    tax1.close()
+    tax2.close()
+
+
+def random_length(max_len):
+    return random.randint(1, max_len)
+
+
+def random_bool(config):
+    return random.choice([True, False])
+
+
+def random_bool_tuples(config):
+    l=[]
+    for i in range(random.randint(1, config['test']['tuplemaxlen'])) :
+        l.append(random.choice([None, random_bool(config)]))
+    return tuple(l)
+
+
+def random_char(config):
+    return str2bytes(random.choice(string.ascii_lowercase))
+
+
+def random_char_tuples(config):
+    l=[]
+    for i in range(random.randint(1, config['test']['tuplemaxlen'])) :
+        l.append(random.choice([None, random_char(config)]))
+    return tuple(l)
+
+
+def random_float(config):
+    return random.randint(0, MAX_INT) + random.random()
+
+
+def random_float_tuples(config):
+    l=[]
+    for i in range(random.randint(1, config['test']['tuplemaxlen'])) :
+        l.append(random.choice([None, random_float(config)]))
+    return tuple(l)
+
+
+def random_int(config):
+    return random.randint(0, config['test']['maxlinenb'])
+
+
+def random_int_tuples(config):
+    l=[]
+    for i in range(random.randint(1, config['test']['tuplemaxlen'])) :
+        l.append(random.choice([None, random_int(config)]))
+    return tuple(l)
+
+
+def random_seq(config):
+    return str2bytes(''.join(random.choice(['a','t','g','c']) for i in range(random_length(config['test']['seqmaxlen']))))
+
+
+def random_seq_tuples(config):
+    l=[]
+    for i in range(random.randint(1, config['test']['tuplemaxlen'])) :
+        l.append(random.choice([None, random_seq(config)]))
+    return tuple(l)
+
+
+def random_bytes(config):
+    return random_bytes_with_max_len(config['test']['strmaxlen'])
+
+
+def random_bytes_tuples(config):
+    l=[]
+    for i in range(random.randint(1, config['test']['tuplemaxlen'])) :
+        l.append(random.choice([None, random_bytes(config)]))
+    return tuple(l)
+
+
+def random_str_with_max_len(max_len):
+    return ''.join(random.choice(string.ascii_lowercase) for i in range(random_length(max_len)))
+
+
+def random_bytes_with_max_len(max_len):
+    return str2bytes(random_str_with_max_len(max_len))
+
+
+RANDOM_FUNCTIONS = [random_bool, random_char, random_bytes, random_float, random_int]
+def random_comments(config):
+    comments = {}
+    for i in range(random_length(1000)):
+        to_add = {random_bytes(config): random.choice(RANDOM_FUNCTIONS)(config)}
+        if len(str(comments)) + len(str(to_add)) >= COL_COMMENTS_MAX_LEN:
+            return comments
+        else:
+            comments.update(to_add)
+    return comments
+    
+ 
+def random_column(infos):
+    return random.choice(sorted(list(infos['view'].keys())))
+ 
+ 
+def random_unique_name(infos):
+    name = b""
+    while name == b"" or name in infos['unique_names'] :
+        name = random_bytes_with_max_len(NAME_MAX_LEN)
+    infos['unique_names'].append(name)
+    return name
+ 
+ 
+def random_unique_element_name(config, infos):
+    name = b""
+    while name == b"" or name in infos['unique_names'] :
+        name = random_bytes_with_max_len(config['test']['elt_name_max_len'])
+    infos['unique_names'].append(name)
+    return name
+ 
+ 
+def print_test(config, sentence):
+    if config['test']['verbose'] :
+        print(sentence)
+ 
+ 
+def test_set_and_get(config, infos):
+    print_test(config, ">>> Set and get test")
+    col_name = random_column(infos)
+    col = infos['view'][col_name]
+    element_names = col.elements_names
+    data_type = col.data_type
+    if data_type == b"OBI_QUAL" :
+        print_test(config, "-")
+        return
+    idx = random_int(config)
+    value = random.choice([None, infos['random_generator'][(data_type, col.tuples)](config)])
+    if col.nb_elements_per_line > 1 :
+        elt = random.choice(element_names)
+        col[idx][elt] = value
+        assert col[idx][elt] == value, "Column: "+repr(col)+"\nSet value != gotten value "+str(value)+" != "+str(col[idx][elt])
+    elif col.tuples:
+        col[idx] = value
+        if value is None:
+            totest = None
+        else:
+            totest = []
+            for e in value:
+                if e is not None and e != '':
+                    totest.append(e)
+            if len(totest) == 0:
+                totest = None
+            else:
+                totest = tuple(totest)
+        assert col[idx] == totest, "Column: "+repr(col)+"\nSet value != gotten value "+str(totest)+" != "+str(col[idx])
+        if totest is not None:
+            for i in range(len(totest)) :
+                assert col[idx][i] == totest[i], "Column: "+repr(col)+"\nSet value[i] != gotten value[i] "+str(totest[i])+" != "+str(col[idx][i])
+    else:
+        col[idx] = value
+        assert col[idx] == value, "Column: "+repr(col)+"\nSet value != gotten value "+str(value)+" != "+str(col[idx])
+    
+    print_test(config, ">>> Set and get test OK")
+
+
+def test_add_col(config, infos):
+    print_test(config, ">>> Add column test")
+    #existing_col = random_bool(config)    # TODO doesn't work because of line count problem. See obiview.c line 1737
+    #if existing_col and infos["view_names"] != [] :
+    #    random_view = infos['dms'].open_view(random.choice(infos["view_names"]))
+    #    random_column = random_view[random.choice(sorted(list(random_view.columns))]
+    #    random_column_refs = random_column.refs
+    #    if random_column_refs['name'] in infos['view'] :
+    #        alias = random_unique_name(infos)
+    #    else :
+    #        alias = ''
+    #    infos['view'].add_column(random_column_refs['name'], version_number=random_column_refs['version'], alias=alias, create=False)
+    #    random_view.close()
+    #else :
+    create_random_column(config, infos)
+    print_test(config, ">>> Add column test OK")
+
+
+def test_delete_col(config, infos):
+    print_test(config, ">>> Delete column test")
+    if len(list(infos['view'].keys())) <= 1 :
+        print_test(config, "-")
+        return
+    col_name = random_column(infos)
+    if col_name in SPECIAL_COLUMNS :
+        print_test(config, "-")
+        return
+    infos['view'].delete_column(col_name)
+    print_test(config, ">>> Delete column test OK")
+
+
+def test_col_alias(config, infos):
+    print_test(config, ">>> Changing column alias test")
+    col_name = random_column(infos)
+    if col_name in SPECIAL_COLUMNS :
+        print_test(config, "-")
+        return
+    infos['view'][col_name].name = random_unique_name(infos)
+    print_test(config, ">>> Changing column alias test OK")
+         
+ 
+def test_new_view(config, infos):
+    print_test(config, ">>> New view test")
+    random_new_view(config, infos)
+    print_test(config, ">>> New view test OK")
+ 
+ 
+def random_test(config, infos):
+    return random.choice(infos['tests'])(config, infos)
+ 
+ 
+def random_view_type():
+    return random.choice(VIEW_TYPES)
+ 
+ 
+def random_col_type():
+    return random.choice(COL_TYPES)    
+ 
+ 
+def fill_column(config, infos, col) :
+    data_type = col.data_type
+    element_names = col.elements_names
+     
+    if len(element_names) > 1 :
+        for i in range(random_int(config)) :
+            for j in range(len(element_names)) :
+                col[i][element_names[j]] = random.choice([None, infos['random_generator'][(data_type, col.tuples)](config)])
+    else :
+        for i in range(random_int(config)) :
+            r = random.choice([None, infos['random_generator'][(data_type, col.tuples)](config)])
+            col[i] = r
+
+
+def create_random_column(config, infos) :
+    alias = random.choice([b'', random_unique_name(infos)])
+    tuples = random.choice([True, False])
+    if not tuples :
+        nb_elements_per_line=random.randint(1, config['test']['maxelts'])
+        elements_names = []
+        for i in range(nb_elements_per_line) :
+            elements_names.append(random_unique_element_name(config, infos))
+        elements_names = random.choice([None, elements_names])
+    else :
+        nb_elements_per_line = 1
+        elements_names = None
+    name = random_unique_name(infos)
+    data_type = random_col_type()
+    
+    column = Column.new_column(infos['view'], 
+                               name, 
+                               data_type, 
+                               nb_elements_per_line=nb_elements_per_line,
+                               elements_names=elements_names,
+                               tuples=tuples,
+                               comments=random_comments(config),
+                               alias=alias
+                               )   
+    
+    if alias != b'' :
+        assert infos['view'][alias] == column
+    else :
+        assert infos['view'][name] == column
+
+    return column
+ 
+ 
+def fill_view(config, infos):
+    for i in range(random.randint(1, config['test']['maxinicolcount'])) :
+        col = create_random_column(config, infos)
+        fill_column(config, infos, col)
+ 
+ 
+def random_new_view(config, infos, first=False):
+    v_to_clone = None
+    line_selection = None
+    quality_col = False     # TODO
+    if not first:
+        infos['view_names'].append(infos['view'].name)
+        infos['view'].close()
+        v_to_clone = View.open(infos['dms'], random.choice(infos["view_names"]))
+        v_type = b""
+        print_test(config, "View to clone: ")
+        print_test(config, repr(v_to_clone))
+        create_line_selection = random_bool(config)
+        if create_line_selection and v_to_clone.line_count > 0:
+            print_test(config, "New view with new line selection.")
+            line_selection = Line_selection(v_to_clone)
+            for i in range(random.randint(1, v_to_clone.line_count)) :
+                line_selection.append(random.randint(0, v_to_clone.line_count-1))
+            #print_test(config, "New line selection: "+str(line_selection))
+    else :
+        v_type = random_view_type()
+     
+    if line_selection is not None :
+        infos['view'] = line_selection.materialize(random_unique_name(infos), comments=random_comments(config))
+    elif v_to_clone is not None :
+        infos['view'] = v_to_clone.clone(random_unique_name(infos), comments=random_comments(config))
+    else :
+        if v_type == "NUC_SEQS_VIEW" :
+            infos['view'] = View_NUC_SEQS.new(infos['dms'], random_unique_name(infos), comments=random_comments(config))   # TODO quality column
+        else :
+            infos['view'] = View.new(infos['dms'], random_unique_name(infos), comments=random_comments(config))   # TODO quality column
+        
+    print_test(config, repr(infos['view']))
+    if v_to_clone is not None :
+        if line_selection is None:
+            assert v_to_clone.line_count == infos['view'].line_count, "New view and cloned view don't have the same line count : "+str(v_to_clone.line_count)+" (view to clone line count) != "+str(infos['view'].line_count)+" (new view line count)"
+        else :
+            assert len(line_selection) == infos['view'].line_count, "New view with new line selection does not have the right line count : "+str(len(line_selection))+" (line selection length) != "+str(infos['view'].line_count)+" (new view line count)"
+        v_to_clone.close()
+    if first :
+        fill_view(config, infos)
+
+
+def create_test_obidms(config, infos):
+    infos['dms'] = DMS.new(config['obi']['defaultdms'])
+
+
+def ini_dms_and_first_view(config, infos):
+    create_test_obidms(config, infos)
+    random_new_view(config, infos, first=True)
+    infos['view_names'] = []
+
+
+def addOptions(parser):
+     
+    # TODO put this common group somewhere else but I don't know where
+    group=parser.add_argument_group('DMS and view options')
+ 
+    group.add_argument('--default-dms','-d', 
+                       action="store", dest="obi:defaultdms",
+                       metavar='<DMS NAME>',
+                       default="/tmp/test_dms",
+                       type=str,
+                       help="Name of the default DMS for reading and writing data. "
+                            "Default: /tmp/test_dms")
+    
+    group.add_argument('--taxo','-t',     # TODO I don't understand why the option is not registered if it is not set
+                       action="store", dest="obi:taxo",
+                       metavar='<TAXDUMP PATH>',
+                       default='',  # TODO not None because if it's None, the option is not entered in the option dictionary.
+                       type=str,
+                       help="Path to a taxdump to test the taxonomy.")
+
+     
+    group=parser.add_argument_group('obi test specific options')
+ 
+    group.add_argument('--nb_tests','-n',
+                       action="store", dest="test:nbtests",
+                       metavar='<NB_TESTS>',
+                       default=1000,
+                       type=int,
+                       help="Number of tests to carry out. "
+                            "Default: 1000")
+ 
+    group.add_argument('--seq_max_len','-s',
+                       action="store", dest="test:seqmaxlen",
+                       metavar='<SEQ_MAX_LEN>',
+                       default=200,
+                       type=int,
+                       help="Maximum length of DNA sequences. "
+                            "Default: 200")
+ 
+    group.add_argument('--str_max_len','-r',
+                       action="store", dest="test:strmaxlen",
+                       metavar='<STR_MAX_LEN>',
+                       default=200,
+                       type=int,
+                       help="Maximum length of character strings. "
+                            "Default: 200")
+
+    group.add_argument('--tuple_max_len','-u',
+                       action="store", dest="test:tuplemaxlen",
+                       metavar='<TUPLE_MAX_LEN>',
+                       default=20,
+                       type=int,
+                       help="Maximum length of tuples. "
+                            "Default: 200")
+  
+    group.add_argument('--max_ini_col_count','-o',
+                       action="store", dest="test:maxinicolcount",
+                       metavar='<MAX_INI_COL_COUNT>',
+                       default=10,
+                       type=int,
+                       help="Maximum number of columns in the initial view. "
+                            "Default: 10")
+ 
+    group.add_argument('--max_line_nb','-l',
+                       action="store", dest="test:maxlinenb",
+                       metavar='<MAX_LINE_NB>',
+                       default=10000,
+                       type=int,
+                       help="Maximum number of lines in a column. "
+                            "Default: 10000")
+ 
+    group.add_argument('--max_elts_per_line','-e',
+                       action="store", dest="test:maxelts",
+                       metavar='<MAX_ELTS_PER_LINE>',
+                       default=20,
+                       type=int,
+                       help="Maximum number of elements per line in a column. "
+                            "Default: 20")
+ 
+    group.add_argument('--verbose','-v',
+                       action="store_true", dest="test:verbose",
+                       default=False,
+                       help="Print the tests. "
+                            "Default: Don't print the tests")
+ 
+    group.add_argument('--seed','-g',
+                       action="store", dest="test:seed",
+                       metavar='<SEED>',
+                       default=None,
+                       help="Seed (use for reproducible tests). "
+                            "Default: Seed is determined by Python")
+ 
+def run(config):
+     
+    if 'seed' in config['test'] :
+        random.seed(config['test']['seed'])
+     
+    infos = {'dms': None, 
+             'view': None, 
+             'view_names': None, 
+             'unique_names': [],
+             'random_generator': {
+                                    (b"OBI_BOOL", False): random_bool, (b"OBI_BOOL", True): random_bool_tuples, 
+                                    (b"OBI_CHAR", False): random_char, (b"OBI_CHAR", True): random_char_tuples, 
+                                    (b"OBI_FLOAT", False): random_float, (b"OBI_FLOAT", True): random_float_tuples, 
+                                    (b"OBI_INT", False): random_int, (b"OBI_INT", True): random_int_tuples, 
+                                    (b"OBI_SEQ", False): random_seq, (b"OBI_SEQ", True): random_seq_tuples,
+                                    (b"OBI_STR", False): random_bytes, (b"OBI_STR", True): random_bytes_tuples
+                                  },
+             'tests': [test_set_and_get, test_add_col, test_delete_col, test_col_alias, test_new_view]
+            }
+ 
+    # TODO ???
+    config['test']['elt_name_max_len'] = int((COL_COMMENTS_MAX_LEN - config['test']['maxelts']) / config['test']['maxelts'])
+ 
+    print("Initializing the DMS and the first view...")
+     
+    shutil.rmtree(config['obi']['defaultdms']+'.obidms', ignore_errors=True)
+    
+    ini_dms_and_first_view(config, infos)
+    print_test(config, repr(infos['view']))
+    
+    i = 0
+    for t in range(config['test']['nbtests']):
+        random_test(config, infos)
+        print_test(config, repr(infos['view']))
+        i+=1
+        if (i%(config['test']['nbtests']/10)) == 0 :
+            print("Testing......"+str(i*100/config['test']['nbtests'])+"%")
+ 
+    #print(infos)
+    
+    if config['obi']['taxo'] != '' :
+        test_taxo(config, infos)
+    
+    infos['view'].close()
+    infos['dms'].close()
+    shutil.rmtree(config['obi']['defaultdms']+'.obidms', ignore_errors=True)
+     
+    print("Done.")
+
+        

python/obitools3/commands/uniq.cfiles

@@ -0,0 +1,103 @@
+../../../src/obi_lcs.h
+../../../src/obi_lcs.c
+../../../src/obierrno.h
+../../../src/obierrno.c
+../../../src/upperband.h
+../../../src/upperband.c
+../../../src/sse_banded_LCS_alignment.h
+../../../src/sse_banded_LCS_alignment.c
+../../../src/obiblob.h
+../../../src/obiblob.c
+../../../src/utils.h
+../../../src/utils.c
+../../../src/obidms.h
+../../../src/obidms.c
+../../../src/libjson/json_utils.h
+../../../src/libjson/json_utils.c
+../../../src/libjson/cJSON.h
+../../../src/libjson/cJSON.c
+../../../src/obiavl.h
+../../../src/obiavl.c
+../../../src/bloom.h
+../../../src/bloom.c
+../../../src/crc64.h
+../../../src/crc64.c
+../../../src/murmurhash2.h
+../../../src/murmurhash2.c
+../../../src/obidmscolumn.h
+../../../src/obidmscolumn.c
+../../../src/obitypes.h
+../../../src/obitypes.c
+../../../src/obidmscolumndir.h
+../../../src/obidmscolumndir.c
+../../../src/obiblob_indexer.h
+../../../src/obiblob_indexer.c
+../../../src/obiview.h
+../../../src/obiview.c
+../../../src/hashtable.h
+../../../src/hashtable.c
+../../../src/linked_list.h
+../../../src/linked_list.c
+../../../src/obidmscolumn_array.h
+../../../src/obidmscolumn_array.c
+../../../src/obidmscolumn_blob.h
+../../../src/obidmscolumn_blob.c
+../../../src/obidmscolumn_idx.h
+../../../src/obidmscolumn_idx.c
+../../../src/obidmscolumn_bool.h
+../../../src/obidmscolumn_bool.c
+../../../src/obidmscolumn_char.h
+../../../src/obidmscolumn_char.c
+../../../src/obidmscolumn_float.h
+../../../src/obidmscolumn_float.c
+../../../src/obidmscolumn_int.h
+../../../src/obidmscolumn_int.c
+../../../src/obidmscolumn_qual.h
+../../../src/obidmscolumn_qual.c
+../../../src/obidmscolumn_seq.h
+../../../src/obidmscolumn_seq.c
+../../../src/obidmscolumn_str.h
+../../../src/obidmscolumn_str.c
+../../../src/array_indexer.h
+../../../src/array_indexer.c
+../../../src/char_str_indexer.h
+../../../src/char_str_indexer.c
+../../../src/dna_seq_indexer.h
+../../../src/dna_seq_indexer.c
+../../../src/encode.c
+../../../src/encode.h
+../../../src/uint8_indexer.c
+../../../src/uint8_indexer.h
+../../../src/build_reference_db.c
+../../../src/build_reference_db.h
+../../../src/kmer_similarity.c
+../../../src/kmer_similarity.h
+../../../src/obi_clean.c
+../../../src/obi_clean.h
+../../../src/obi_ecopcr.c
+../../../src/obi_ecopcr.h
+../../../src/obi_ecotag.c
+../../../src/obi_ecotag.h
+../../../src/obidms_taxonomy.c
+../../../src/obidms_taxonomy.h
+../../../src/obilittlebigman.c
+../../../src/obilittlebigman.h
+../../../src/_sse.h
+../../../src/obidebug.h
+../../../src/libecoPCR/libapat/CODES/dft_code.h
+../../../src/libecoPCR/libapat/CODES/dna_code.h
+../../../src/libecoPCR/libapat/CODES/prot_code.h
+../../../src/libecoPCR/libapat/apat_parse.c
+../../../src/libecoPCR/libapat/apat_search.c
+../../../src/libecoPCR/libapat/apat.h
+../../../src/libecoPCR/libapat/Gmach.h
+../../../src/libecoPCR/libapat/Gtypes.h
+../../../src/libecoPCR/libapat/libstki.c
+../../../src/libecoPCR/libapat/libstki.h
+../../../src/libecoPCR/libthermo/nnparams.h
+../../../src/libecoPCR/libthermo/nnparams.c
+../../../src/libecoPCR/ecoapat.c
+../../../src/libecoPCR/ecodna.c
+../../../src/libecoPCR/ecoError.c
+../../../src/libecoPCR/ecoMalloc.c
+../../../src/libecoPCR/ecoPCR.h

python/obitools3/commands/uniq.pxd

@@ -0,0 +1,9 @@
+#cython: language_level=3
+
+from obitools3.apps.progress cimport ProgressBar  # @UnresolvedImport
+from obitools3.dms.taxo.taxo cimport Taxonomy
+from obitools3.dms.view.typed_view.view_NUC_SEQS cimport View_NUC_SEQS
+
+
+cdef merge_taxonomy_classification(View_NUC_SEQS o_view, Taxonomy taxonomy)
+cdef uniq_sequences(View_NUC_SEQS view, View_NUC_SEQS o_view, ProgressBar pb, list mergedKeys_list=*, Taxonomy taxonomy=*, bint mergeIds=*, list categories=*, int max_elts=*)

python/obitools3/commands/uniq.pyx

@@ -0,0 +1,542 @@
+#cython: language_level=3
+
+from obitools3.apps.progress cimport ProgressBar  # @UnresolvedImport
+from obitools3.dms import DMS
+from obitools3.dms.view.view cimport View
+from obitools3.dms.obiseq cimport Nuc_Seq_Stored
+from obitools3.dms.view import RollbackException
+from obitools3.dms.view.typed_view.view_NUC_SEQS cimport View_NUC_SEQS
+from obitools3.dms.column.column cimport Column, Column_line
+from obitools3.dms.capi.obiview cimport QUALITY_COLUMN, COUNT_COLUMN, NUC_SEQUENCE_COLUMN, ID_COLUMN
+from obitools3.dms.capi.obitypes cimport OBI_INT, OBI_STR, index_t
+from obitools3.apps.optiongroups import addMinimalInputOption, addMinimalOutputOption, addTaxonomyOption
+from obitools3.uri.decode import open_uri
+from obitools3.apps.config import logger
+from obitools3.utils cimport tobytes
+
+import sys
+
+
+__title__="Group sequence records together"
+ 
+
+ 
+def addOptions(parser):
+ 
+    addMinimalInputOption(parser)
+    addTaxonomyOption(parser)
+    addMinimalOutputOption(parser)
+ 
+    group = parser.add_argument_group('obi uniq specific options')
+ 
+    group.add_argument('--merge', '-m',
+                       action="append", dest="uniq:merge",
+                       metavar="<TAG NAME>",
+                       default=[],
+                       type=str,
+                       help="Attributes to merge.")     # TODO must be a 1 elt/line column
+
+    group.add_argument('--merge-ids', '-e',
+                       action="store_true", dest="uniq:mergeids",
+                       default=False,
+                       help="ONLY WORKING ON SMALL SETS FOR NOW Add the merged key with all ids of merged sequences.")  # TODO ?
+   
+    group.add_argument('--category-attribute', '-c',
+                        action="append", dest="uniq:categories",
+                        metavar="<Attribute Name>",
+                        default=[],
+                        help="Add one attribute to the list of attributes "
+                             "used to group sequences before dereplication "
+                             "(option can be used several times).")
+
+
+cdef merge_taxonomy_classification(View_NUC_SEQS o_view, Taxonomy taxonomy) :
+    
+    cdef int             taxid
+    cdef Nuc_Seq_Stored  seq
+    cdef list            m_taxids
+    cdef bytes           k
+    cdef object          tsp
+    cdef object          tgn
+    cdef object          tfa
+    cdef object          sp_sn
+    cdef object          gn_sn
+    cdef object          fa_sn
+
+    # Create columns
+    if b"species" in o_view and o_view[b"species"].data_type_int != OBI_INT :
+        o_view.delete_column(b"species")
+    if b"species" not in o_view:
+        Column.new_column(o_view, 
+                          b"species", 
+                          OBI_INT
+                         )
+
+    if b"genus" in o_view and o_view[b"genus"].data_type_int != OBI_INT :
+        o_view.delete_column(b"genus")
+    if b"genus" not in o_view:
+        Column.new_column(o_view, 
+                          b"genus", 
+                          OBI_INT
+                         )
+
+    if b"family" in o_view and o_view[b"family"].data_type_int != OBI_INT :
+        o_view.delete_column(b"family")
+    if b"family" not in o_view:
+        Column.new_column(o_view, 
+                          b"family", 
+                          OBI_INT
+                         )
+
+    if b"species_name" in o_view and o_view[b"species_name"].data_type_int != OBI_STR :
+        o_view.delete_column(b"species_name")
+    if b"species_name" not in o_view:
+        Column.new_column(o_view, 
+                          b"species_name", 
+                          OBI_STR
+                         )
+
+    if b"genus_name" in o_view and o_view[b"genus_name"].data_type_int != OBI_STR :
+        o_view.delete_column(b"genus_name")
+    if b"genus_name" not in o_view:
+        Column.new_column(o_view, 
+                          b"genus_name", 
+                          OBI_STR
+                         )
+
+    if b"family_name" in o_view and o_view[b"family_name"].data_type_int != OBI_STR :
+        o_view.delete_column(b"family_name")
+    if b"family_name" not in o_view:
+        Column.new_column(o_view, 
+                          b"family_name", 
+                          OBI_STR
+                         )
+
+    if b"rank" in o_view and o_view[b"rank"].data_type_int != OBI_STR :
+        o_view.delete_column(b"rank")
+    if b"rank" not in o_view:
+        Column.new_column(o_view, 
+                          b"rank", 
+                          OBI_STR
+                         )
+
+    if b"scientific_name" in o_view and o_view[b"scientific_name"].data_type_int != OBI_STR :
+        o_view.delete_column(b"scientific_name")
+    if b"scientific_name" not in o_view:
+        Column.new_column(o_view, 
+                          b"scientific_name", 
+                          OBI_STR
+                         )
+        
+    for seq in o_view:        
+        if b"merged_taxid" in seq :
+            m_taxids = []            
+            m_taxids_dict = seq[b"merged_taxid"]
+            for k in m_taxids_dict.keys() :
+                if m_taxids_dict[k] is not None:
+                    m_taxids.append(int(k))
+            taxid = taxonomy.last_common_taxon(*m_taxids)
+            seq[b"taxid"] = taxid
+            tsp = taxonomy.get_species(taxid)
+            tgn = taxonomy.get_genus(taxid)
+            tfa = taxonomy.get_family(taxid)
+            
+            if tsp is not None:
+                sp_sn = taxonomy.get_scientific_name(tsp)
+            else:
+                sp_sn = None   # TODO was '###', discuss
+                tsp = None     # TODO was '-1', discuss
+                
+            if tgn is not None:
+                gn_sn = taxonomy.get_scientific_name(tgn)
+            else:
+                gn_sn = None
+                tgn = None
+                
+            if tfa is not None:
+                fa_sn = taxonomy.get_scientific_name(tfa)
+            else:
+                fa_sn = None
+                tfa = None
+                
+            seq[b"species"] = tsp
+            seq[b"genus"] = tgn
+            seq[b"family"] = tfa
+                
+            seq[b"species_name"] = sp_sn
+            seq[b"genus_name"] = gn_sn
+            seq[b"family_name"] = fa_sn
+            
+            seq[b"rank"] = taxonomy.get_rank(taxid)
+            seq[b"scientific_name"] = taxonomy.get_scientific_name(taxid)
+
+
+cdef uniq_sequences(View_NUC_SEQS view, View_NUC_SEQS o_view, ProgressBar pb, list mergedKeys_list=None, Taxonomy taxonomy=None, bint mergeIds=False, list categories=None, int max_elts=10000) :
+     
+    cdef int            i
+    cdef int            k
+    cdef int            k_count
+    cdef int            o_idx
+    cdef int            u_idx
+    cdef int            i_idx
+    cdef int            i_count
+    cdef str            key_str
+    cdef bytes          key
+    cdef bytes          mkey
+    cdef bytes          merged_col_name
+    cdef bytes          o_id
+    cdef bytes          i_id
+    cdef set            mergedKeys_set
+    cdef tuple          unique_id
+    cdef list           catl
+    cdef list           mergedKeys
+    cdef list           mergedKeys_list_b
+    cdef list           mergedKeys_m
+    cdef list           str_merged_cols
+    cdef list           merged_sequences
+    cdef dict           uniques
+    cdef dict           merged_infos
+    cdef dict           mkey_infos
+    cdef dict           merged_dict
+    cdef dict           mkey_cols
+    cdef Nuc_Seq_Stored i_seq
+    cdef Nuc_Seq_Stored o_seq
+    cdef Nuc_Seq_Stored u_seq
+    cdef Column         i_col
+    cdef Column         i_seq_col
+    cdef Column         i_id_col
+    cdef Column         i_taxid_col
+    cdef Column         i_taxid_dist_col
+    cdef Column         o_id_col
+    cdef Column         o_taxid_dist_col
+    cdef Column         o_merged_col
+    cdef Column_line    i_mcol  
+    cdef object         taxid_dist_dict
+    cdef object         iter_view
+    cdef object         mcol
+    cdef object         to_merge
+
+    uniques = {}
+    
+    mergedKeys_list_b = []
+    if mergedKeys_list is not None:
+        for key_str in mergedKeys_list:
+            mergedKeys_list_b.append(tobytes(key_str))
+        mergedKeys_set=set(mergedKeys_list_b)
+    else:
+        mergedKeys_set=set() 
+ 
+    if taxonomy is not None:
+        mergedKeys_set.add(b"taxid")
+         
+    mergedKeys = list(mergedKeys_set)
+     
+    k_count = len(mergedKeys)
+     
+    mergedKeys_m = []
+    for k in range(k_count):
+        mergedKeys_m.append(b"merged_" + mergedKeys[k])
+     
+    if categories is None:
+        categories = []
+ 
+    # Keep columns that are going to be used a lot in variables 
+    i_seq_col = view[NUC_SEQUENCE_COLUMN]
+    i_id_col = view[ID_COLUMN]
+    if b"taxid" in view:
+        i_taxid_col = view[b"taxid"]
+    if b"taxid_dist" in view:
+        i_taxid_dist_col = view[b"taxid_dist"]
+
+ 
+    # First browsing
+    i = 0
+    o_idx = 0
+    
+    logger("info", "First browsing through the input")
+    merged_infos = {}
+    iter_view = iter(view)
+    for i_seq in iter_view :
+        pb(i)
+         
+        # This can't be done in the same line as the unique_id tuple creation because it generates a bug
+        # where Cython (version 0.25.2) does not detect the reference to the categs_list variable and deallocates 
+        # it at the beginning of the function.
+        # (Only happens if categs_list is an optional parameter, which it is).
+        catl = []
+        for x in categories :
+            catl.append(i_seq[x])    
+          
+        unique_id = tuple(catl) + (i_seq_col.get_line_idx(i),)
+        #unique_id = tuple(i_seq[x] for x in categories) + (seq_col.get_line_idx(i),)  # The line that cython can't read properly
+         
+        if unique_id in uniques:
+            uniques[unique_id].append(i)
+        else:
+            uniques[unique_id] = [i]
+
+        for k in range(k_count):
+            key = mergedKeys[k]
+            mkey = mergedKeys_m[k]
+            if key in i_seq:    # TODO what if mkey already in i_seq?  --> should update
+                if mkey not in merged_infos:
+                    merged_infos[mkey] = {}
+                    mkey_infos = merged_infos[mkey]
+                    mkey_infos['nb_elts'] = 1
+                    mkey_infos['elt_names'] = [i_seq[key]]
+                else:
+                    mkey_infos = merged_infos[mkey]
+                    if i_seq[key] not in mkey_infos['elt_names']:     # TODO make faster? but how?
+                        mkey_infos['elt_names'].append(i_seq[key])
+                        mkey_infos['nb_elts'] += 1
+        i+=1
+
+    # Create merged columns
+    str_merged_cols = []
+    mkey_cols = {}
+    for k in range(k_count):
+        key = mergedKeys[k]
+        merged_col_name = mergedKeys_m[k]
+        i_col = view[key]
+        if merged_infos[merged_col_name]['nb_elts'] > max_elts:
+            str_merged_cols.append(merged_col_name)
+            Column.new_column(o_view,
+                              merged_col_name,
+                              OBI_STR,
+                              to_eval=True,
+                              comments=i_col.comments,
+                              alias=merged_col_name     # TODO what if it already exists
+                             )
+
+        else:
+            Column.new_column(o_view,
+                              merged_col_name,
+                              OBI_INT,
+                              nb_elements_per_line=merged_infos[merged_col_name]['nb_elts'],
+                              elements_names=list(merged_infos[merged_col_name]['elt_names']),
+                              comments=i_col.comments,
+                              alias=merged_col_name     # TODO what if it already exists
+                             )
+        
+        mkey_cols[merged_col_name] = o_view[merged_col_name]
+
+    # taxid_dist column
+    if mergeIds and b"taxid" in mergedKeys:
+        if len(view) > max_elts: #The number of different IDs corresponds to the number of sequences in the view
+            str_merged_cols.append(b"taxid_dist")
+            Column.new_column(o_view, 
+                              b"taxid_dist", 
+                              OBI_STR,
+                              to_eval=True,
+                              comments=b"obi uniq taxid dist, stored as character strings to be read as dict",
+                              alias=b"taxid_dist"     # TODO what if it already exists
+                             )
+        else:
+            Column.new_column(o_view, 
+                              b"taxid_dist", 
+                              OBI_INT,
+                              nb_elements_per_line=len(view),
+                              elements_names=[id for id in i_id_col],
+                              comments=b"obi uniq taxid dist",
+                              alias=b"taxid_dist"     # TODO what if it already exists
+                             )
+            
+
+    del(merged_infos)
+    
+    # Merged ids column
+    if mergeIds :
+        Column.new_column(o_view,
+                          b"merged",
+                          OBI_STR,
+                          tuples=True,
+                          comments=b"obi uniq merged ids",
+                          alias=b"merged"     # TODO what if it already exists
+                         )
+
+
+    # Keep columns that are going to be used a lot in variables 
+    o_id_col = o_view[ID_COLUMN]
+    if b"taxid_dist" in o_view:
+        o_taxid_dist_col = o_view[b"taxid_dist"]
+    if b"merged" in o_view:
+        o_merged_col = o_view[b"merged"]
+        
+    print("\n")  # TODO because in the middle of progress bar. Better solution?
+    logger("info", "Second browsing through the input")
+    # Initialize the progress bar
+    pb = ProgressBar(len(uniques), seconde=5)
+    o_idx = 0
+    
+    for unique_id in uniques :
+        pb(o_idx)
+        
+        merged_sequences = uniques[unique_id]
+        
+        u_idx = uniques[unique_id][0]
+        u_seq = view[u_idx]
+        o_view[o_idx] = u_seq
+        o_seq = o_view[o_idx]
+        o_id = o_seq.id
+        
+        if mergeIds:
+            o_merged_col[o_idx] = [view[idx].id for idx in merged_sequences]
+
+        o_seq[COUNT_COLUMN] = 0
+
+        if b"taxid_dist" in u_seq and i_taxid_dist_col[u_idx] is not None:
+            taxid_dist_dict = i_taxid_dist_col[u_idx]
+        else:
+            taxid_dist_dict = {}           
+
+        merged_dict = {}
+        for mkey in mergedKeys_m:
+            merged_dict[mkey] = {}
+
+        for i_idx in merged_sequences:
+                        
+            i_id = i_id_col[i_idx]
+            i_seq = view[i_idx]
+
+            if COUNT_COLUMN not in i_seq or i_seq[COUNT_COLUMN] is None:
+                i_count = 1
+            else:
+                i_count = i_seq[COUNT_COLUMN]
+ 
+            o_seq[COUNT_COLUMN] += i_count
+                                               
+            for k in range(k_count):
+                                
+                key = mergedKeys[k]
+                mkey = mergedKeys_m[k]
+                
+                if key==b"taxid" and mergeIds:
+                    if b"taxid_dist" in i_seq:
+                        taxid_dist_dict.update(i_taxid_dist_col[i_idx])
+                    if b"taxid" in i_seq:
+                        taxid_dist_dict[i_id] = i_taxid_col[i_idx]
+
+                #cas ou on met a jour les merged_keys mais il n'y a pas de merged_keys dans la sequence qui arrive
+                if key in i_seq:
+                    to_merge = i_seq[key]
+                    if to_merge is not None:
+                        if type(to_merge) != bytes:
+                            to_merge = tobytes(str(to_merge))
+                        mcol = merged_dict[mkey]
+                        if to_merge not in mcol or mcol[to_merge] is None:
+                            mcol[to_merge] = i_count
+                        else:
+                            mcol[to_merge] = mcol[to_merge] + i_count
+                        o_seq[key] = None
+                #cas ou merged_keys existe deja
+                else:   # TODO is this a good else
+                    if mkey in i_seq:
+                        mcol = merged_dict[mkey]
+                        i_mcol = i_seq[mkey]
+                        if i_mcol is not None:
+                            for key2 in i_mcol:
+                                if mcol[key2] is None:
+                                    mcol[key2] = i_mcol[key2]
+                                else:
+                                    mcol[key2] = mcol[key2] + i_mcol[key2]
+            
+            # Write taxid_dist
+            if mergeIds and b"taxid" in mergedKeys:
+                if b"taxid_dist" in str_merged_cols:
+                    o_taxid_dist_col[o_idx] = str(taxid_dist_dict)
+                else:
+                    o_taxid_dist_col[o_idx] = taxid_dist_dict
+            
+            # Write merged dicts
+            for mkey in merged_dict: 
+                if mkey in str_merged_cols:
+                    mkey_cols[mkey][o_idx] = str(merged_dict[mkey])
+                else:
+                    mkey_cols[mkey][o_idx] = merged_dict[mkey]
+                    # Sets NA values to 0  # TODO discuss, maybe keep as None and test for None instead of testing for 0 in tools
+                    #for key in mkey_cols[mkey][o_idx]:
+                    #    if mkey_cols[mkey][o_idx][key] is None:
+                    #        mkey_cols[mkey][o_idx][key] = 0
+                            
+            for key in i_seq.keys():
+                # Delete informations that differ between the merged sequences
+                # TODO make special columns list?
+                if key != COUNT_COLUMN and key != ID_COLUMN and key != NUC_SEQUENCE_COLUMN and key in o_seq and o_seq[key] != i_seq[key] :
+                    o_seq[key] = None
+
+        o_idx += 1
+    
+    # Deletes quality column if there is one because the matching between sequence and quality will be broken (quality set to NA when sequence not)
+    if QUALITY_COLUMN in view:
+        o_view.delete_column(QUALITY_COLUMN)
+    
+    if taxonomy is not None:
+        print("\n")  # TODO because in the middle of progress bar. Better solution?
+        logger("info", "Merging taxonomy classification")
+        merge_taxonomy_classification(o_view, taxonomy)
+
+
+
+def run(config):
+    
+    cdef tuple         input
+    cdef tuple         output 
+    cdef tuple         taxo_uri
+    cdef Taxonomy      taxo
+    cdef View_NUC_SEQS entries
+    cdef View_NUC_SEQS o_view
+    cdef ProgressBar   pb
+    
+    DMS.obi_atexit()
+    
+    logger("info","obi uniq")
+    
+    # Open the input
+    input = open_uri(config['obi']['inputURI'])
+    if input is None:
+        raise Exception("Could not read input view")    
+    if input[2] != View_NUC_SEQS:
+        raise NotImplementedError('obi uniq only works on NUC_SEQS views')
+    
+    # Open the output
+    output = open_uri(config['obi']['outputURI'],
+                      input=False,
+                      newviewtype=View_NUC_SEQS)
+    if output is None:
+        raise Exception("Could not create output view")
+    
+    entries = input[1]
+    o_view = output[1]
+    
+    if 'taxoURI' in config['obi'] and config['obi']['taxoURI'] is not None:
+        taxo_uri = open_uri(config['obi']['taxoURI'])
+        if taxo_uri is None:
+            raise RollbackException("Couldn't open taxonomy, rollbacking view", o_view)
+        taxo = taxo_uri[1]
+    else :
+        taxo = None
+
+    # Initialize the progress bar
+    pb = ProgressBar(len(entries), config, seconde=5)
+    
+    try:
+        uniq_sequences(entries, o_view, pb, mergedKeys_list=config['uniq']['merge'], taxonomy=taxo, mergeIds=config['uniq']['mergeids'], categories=config['uniq']['categories'], max_elts=config['obi']['maxelts'])       
+    except Exception, e:
+        raise RollbackException("obi uniq error, rollbacking view: "+str(e), o_view)
+    
+    # Save command config in View and DMS comments
+    command_line = " ".join(sys.argv[1:])
+    input_dms_name=[input[0].name]
+    input_view_name=[input[1].name]
+    if 'taxoURI' in config['obi'] and config['obi']['taxoURI'] is not None:
+        input_dms_name.append(config['obi']['taxoURI'].split("/")[-3])
+        input_view_name.append("taxonomy/"+config['obi']['taxoURI'].split("/")[-1])
+    o_view.write_config(config, "uniq", command_line, input_dms_name=input_dms_name, input_view_name=input_view_name)
+    output[0].record_command_line(command_line)
+
+    print("\n")
+    print(repr(o_view))
+    
+    input[0].close()
+    output[0].close()
+