From f1a424343c96effd8e5c647cb5a9c1c885dd528c Mon Sep 17 00:00:00 2001 From: Eric Coissac Date: Thu, 2 Jul 2026 08:45:47 +0200 Subject: [PATCH] Update ignore patterns, configure Serena, and refactor FASTSEQ parser Adds `.gitignore` rules to exclude benchmark outputs and local build artifacts. Initializes Serena AI configuration for the Go project with UTF-8 encoding and gitignore-based file exclusion. Refactors the FASTSEQ header parser to fix regex syntax, optimize alternation ordering, improve control flow readability, and introduce explicit float-to-int coercion that preserves fractional values. --- .gitignore | 2 + .serena/.gitignore | 2 + .serena/project.yml | 133 +++++++++++++++++++++++++++ pkg/obiformats/fastseq_obi_header.go | 38 ++++---- 4 files changed, 157 insertions(+), 18 deletions(-) create mode 100644 .serena/.gitignore create mode 100644 .serena/project.yml diff --git a/.gitignore b/.gitignore index 4404995..78e7cbd 100644 --- a/.gitignore +++ b/.gitignore @@ -21,6 +21,8 @@ xx .rhistory /.vscode + +/benchmarck /build /bugs autodoc diff --git a/.serena/.gitignore b/.serena/.gitignore new file mode 100644 index 0000000..2e510af --- /dev/null +++ b/.serena/.gitignore @@ -0,0 +1,2 @@ +/cache +/project.local.yml diff --git a/.serena/project.yml b/.serena/project.yml new file mode 100644 index 0000000..f09dc2a --- /dev/null +++ b/.serena/project.yml @@ -0,0 +1,133 @@ +# the name by which the project can be referenced within Serena +project_name: "obitools4" + + +# list of languages for which language servers are started; choose from: +# al angular ansible bash clojure +# cpp cpp_ccls crystal csharp csharp_omnisharp +# dart elixir elm erlang fortran +# fsharp go groovy haskell haxe +# hlsl html java json julia +# kotlin lean4 lua luau markdown +# matlab msl nix ocaml pascal +# perl php php_phpactor powershell python +# python_jedi python_ty r rego ruby +# ruby_solargraph rust scala scss solidity +# svelte swift systemverilog terraform toml +# typescript typescript_vts vue yaml zig +# (This list may be outdated. For the current list, see values of Language enum here: +# https://github.com/oraios/serena/blob/main/src/solidlsp/ls_config.py +# For some languages, there are alternative language servers, e.g. csharp_omnisharp, ruby_solargraph.) +# Note: +# - For C, use cpp +# - For JavaScript, use typescript +# - For Angular projects, use angular (subsumes typescript+html; requires `npm install` in the project root) +# - For Svelte projects, use svelte (subsumes typescript/javascript for .svelte projects; requires npm) +# - For SCSS / Sass / plain CSS, use scss (some-sass-language-server handles all three) +# - For Free Pascal/Lazarus, use pascal +# Special requirements: +# Some languages require additional setup/installations. +# See here for details: https://oraios.github.io/serena/01-about/020_programming-languages.html#language-servers +# When using multiple languages, the first language server that supports a given file will be used for that file. +# The first language is the default language and the respective language server will be used as a fallback. +# Note that when using the JetBrains backend, language servers are not used and this list is correspondingly ignored. +languages: +- go + +# the encoding used by text files in the project +# For a list of possible encodings, see https://docs.python.org/3.11/library/codecs.html#standard-encodings +encoding: "utf-8" + +# line ending convention to use when writing source files. +# Possible values: unset (use global setting), "lf", "crlf", or "native" (platform default) +# This does not affect Serena's own files (e.g. memories and configuration files), which always use native line endings. +line_ending: + +# The language backend to use for this project. +# If not set, the global setting from serena_config.yml is used. +# Valid values: LSP, JetBrains +# Note: the backend is fixed at startup. If a project with a different backend +# is activated post-init, an error will be returned. +language_backend: + +# whether to use project's .gitignore files to ignore files +ignore_all_files_in_gitignore: true + +# advanced configuration option allowing to configure language server-specific options. +# Maps the language key to the options. +# Have a look at the docstring of the constructors of the LS implementations within solidlsp (e.g., for C# or PHP) to see which options are available. +# No documentation on options means no options are available. +ls_specific_settings: {} + +# list of additional workspace folder paths for cross-package reference support (e.g. in monorepos). +# Paths can be absolute or relative to the project root. +# Each folder is registered as an LSP workspace folder, enabling language servers to discover +# symbols and references across package boundaries. +# Currently supported for: TypeScript. +# Example: +# additional_workspace_folders: +# - ../sibling-package +# - ../shared-lib +additional_workspace_folders: [] + +# list of additional paths to ignore in this project. +# Same syntax as gitignore, so you can use * and **. +# Note: global ignored_paths from serena_config.yml are also applied additively. +ignored_paths: [] + +# whether the project is in read-only mode +# If set to true, all editing tools will be disabled and attempts to use them will result in an error +# Added on 2025-04-18 +read_only: false + +# list of tool names to exclude. +# This extends the existing exclusions (e.g. from the global configuration) +# Find the list of tools here: https://oraios.github.io/serena/01-about/035_tools.html +excluded_tools: [] + +# list of tools to include that would otherwise be disabled (particularly optional tools that are disabled by default). +# This extends the existing inclusions (e.g. from the global configuration). +# Find the list of tools here: https://oraios.github.io/serena/01-about/035_tools.html +included_optional_tools: [] + +# fixed set of tools to use as the base tool set (if non-empty), replacing Serena's default set of tools. +# This cannot be combined with non-empty excluded_tools or included_optional_tools. +# Find the list of tools here: https://oraios.github.io/serena/01-about/035_tools.html +fixed_tools: [] + +# list of mode names that are to be activated by default, overriding the setting in the global configuration. +# The full set of modes to be activated is base_modes (from global config) + default_modes + added_modes. +# If the setting is undefined/empty, the default_modes from the global configuration (serena_config.yml) apply. +# Otherwise, this overrides the setting from the global configuration (serena_config.yml). +# Therefore, you can set this to [] if you do not want the default modes defined in the global config to apply +# for this project. +# This setting can, in turn, be overridden by CLI parameters (--mode). +# See https://oraios.github.io/serena/02-usage/050_configuration.html#modes +default_modes: + +# list of mode names to be activated additionally for this project, e.g. ["query-projects"] +# The full set of modes to be activated is base_modes (from global config) + default_modes + added_modes. +# See https://oraios.github.io/serena/02-usage/050_configuration.html#modes +added_modes: + +# initial prompt for the project. It will always be given to the LLM upon activating the project +# (contrary to the memories, which are loaded on demand). +initial_prompt: "" + +# time budget (seconds) per tool call for the retrieval of additional symbol information +# such as docstrings or parameter information. +# This overrides the corresponding setting in the global configuration; see the documentation there. +# If null or missing, use the setting from the global configuration. +symbol_info_budget: + +# list of regex patterns which, when matched, mark a memory entry as read‑only. +# Extends the list from the global configuration, merging the two lists. +read_only_memory_patterns: [] + +# list of regex patterns for memories to completely ignore. +# Matching memories will not appear in list_memories or activate_project output +# and cannot be accessed via read_memory or write_memory. +# To access ignored memory files, use the read_file tool on the raw file path. +# Extends the list from the global configuration, merging the two lists. +# Example: ["_archive/.*", "_episodes/.*"] +ignored_memory_patterns: [] diff --git a/pkg/obiformats/fastseq_obi_header.go b/pkg/obiformats/fastseq_obi_header.go index fb2fb78..14de9a5 100644 --- a/pkg/obiformats/fastseq_obi_header.go +++ b/pkg/obiformats/fastseq_obi_header.go @@ -17,7 +17,7 @@ import ( ) var __obi_header_value_string_pattern__ = regexp.MustCompile(`^'\s*([^']*'|"[^"]*")\s*;`) -var __obi_header_value_numeric_pattern__ = regexp.MustCompile(`^\s*([+-]?\.\d+|[+-]?\d+(\.\d*)?([eE][+-]?\d+)?)\s*;`) +var __obi_header_value_numeric_pattern__ = regexp.MustCompile(`^\s*[+-]?(\d+(\.\d*)?|\.\d+)([eE][+-]?\d+)?\s*;`) var __obi_header_map_int_key__ = regexp.MustCompile("([{,])([0-9]+):") func __match__dict__(text []byte) []int { @@ -316,28 +316,28 @@ func ParseOBIFeatures(text string, annotations obiseq.Annotation) string { stop = m[1] + 1 } else { - // Generic value + // Generic value - // m = __obi_header_value_general_pattern__.FindIndex(part) - m = __match__general__(part) - if len(m) > 0 { - bvalue = bytes.TrimSpace(part[m[0]:(m[1] - 1)]) + // m = __obi_header_value_general_pattern__.FindIndex(part) + m = __match__general__(part) + if len(m) > 0 { + bvalue = bytes.TrimSpace(part[m[0]:(m[1] - 1)]) - if __is_false__(bvalue) { - value = false - } else { - if __is_true__(bvalue) { - value = true + if __is_false__(bvalue) { + value = false } else { - value = string(bvalue) + if __is_true__(bvalue) { + value = true + } else { + value = string(bvalue) + } } - } - stop = m[1] + 1 - } else { - // no value - break - } // End of No value + stop = m[1] + 1 + } else { + // no value + break + } // End of No value } // End of not array } // End of not dict } // End of not string @@ -347,6 +347,8 @@ func ParseOBIFeatures(text string, annotations obiseq.Annotation) string { case float64: if vt == math.Floor(vt) { annotations[key] = int(vt) + } else { + annotations[key] = vt } default: annotations[key] = value