From 9e8a7fd9be70d1385fa977885f5663bce2a3b1a3 Mon Sep 17 00:00:00 2001 From: Eric Coissac Date: Sun, 20 Oct 2024 16:07:43 +0200 Subject: [PATCH] Patch a bug in fastq reader --- go.mod | 10 +--------- go.sum | 27 --------------------------- pkg/obiformats/fastqseq_read.go | 20 +++++++++++++++++--- pkg/obiformats/seqfile_chunk_read.go | 2 ++ pkg/obioptions/version.go | 2 +- 5 files changed, 21 insertions(+), 40 deletions(-) diff --git a/go.mod b/go.mod index eae59b9..3c8ffbe 100644 --- a/go.mod +++ b/go.mod @@ -7,6 +7,7 @@ require ( github.com/PaesslerAG/gval v1.2.2 github.com/barkimedes/go-deepcopy v0.0.0-20220514131651-17c30cfc62df github.com/chen3feng/stl4go v0.1.1 + github.com/dlclark/regexp2 v1.11.4 github.com/goccy/go-json v0.10.3 github.com/klauspost/pgzip v1.2.6 github.com/pbnjay/memory v0.0.0-20210728143218-7b4eea64cf58 @@ -23,21 +24,12 @@ require ( ) require ( - github.com/bytedance/sonic v1.11.9 // indirect - github.com/bytedance/sonic/loader v0.1.1 // indirect - github.com/cloudwego/base64x v0.1.4 // indirect - github.com/cloudwego/iasm v0.2.0 // indirect github.com/davecgh/go-spew v1.1.1 // indirect - github.com/dlclark/regexp2 v1.11.4 // indirect github.com/goombaio/orderedmap v0.0.0-20180924084748-ba921b7e2419 // indirect - github.com/klauspost/cpuid/v2 v2.0.9 // indirect github.com/kr/pretty v0.3.0 // indirect github.com/kr/text v0.2.0 // indirect - github.com/montanaflynn/stats v0.7.1 // indirect github.com/pmezard/go-difflib v1.0.0 // indirect github.com/rogpeppe/go-internal v1.6.1 // indirect - github.com/twitchyliquid64/golang-asm v0.15.1 // indirect - golang.org/x/arch v0.0.0-20210923205945-b76863e36670 // indirect ) require ( diff --git a/go.sum b/go.sum index fa803db..4b962f4 100644 --- a/go.sum +++ b/go.sum @@ -6,16 +6,8 @@ github.com/PaesslerAG/jsonpath v0.1.0 h1:gADYeifvlqK3R3i2cR5B4DGgxLXIPb3TRTH1mGi github.com/PaesslerAG/jsonpath v0.1.0/go.mod h1:4BzmtoM/PI8fPO4aQGIusjGxGir2BzcV0grWtFzq1Y8= github.com/barkimedes/go-deepcopy v0.0.0-20220514131651-17c30cfc62df h1:GSoSVRLoBaFpOOds6QyY1L8AX7uoY+Ln3BHc22W40X0= github.com/barkimedes/go-deepcopy v0.0.0-20220514131651-17c30cfc62df/go.mod h1:hiVxq5OP2bUGBRNS3Z/bt/reCLFNbdcST6gISi1fiOM= -github.com/bytedance/sonic v1.11.9 h1:LFHENlIY/SLzDWverzdOvgMztTxcfcF+cqNsz9pK5zg= -github.com/bytedance/sonic v1.11.9/go.mod h1:LysEHSvpvDySVdC2f87zGWf6CIKJcAvqab1ZaiQtds4= -github.com/bytedance/sonic/loader v0.1.1 h1:c+e5Pt1k/cy5wMveRDyk2X4B9hF4g7an8N3zCYjJFNM= -github.com/bytedance/sonic/loader v0.1.1/go.mod h1:ncP89zfokxS5LZrJxl5z0UJcsk4M4yY2JpfqGeCtNLU= github.com/chen3feng/stl4go v0.1.1 h1:0L1+mDw7pomftKDruM23f1mA7miavOj6C6MZeadzN2Q= github.com/chen3feng/stl4go v0.1.1/go.mod h1:5ml3psLgETJjRJnMbPE+JiHLrCpt+Ajc2weeTECXzWU= -github.com/cloudwego/base64x v0.1.4 h1:jwCgWpFanWmN8xoIUHa2rtzmkd5J2plF/dnLS6Xd/0Y= -github.com/cloudwego/base64x v0.1.4/go.mod h1:0zlkT4Wn5C6NdauXdJRhSKRlJvmclQ1hhJgA0rcu/8w= -github.com/cloudwego/iasm v0.2.0 h1:1KNIy1I1H9hNNFEEH3DVnI4UujN+1zjpuk6gwHLTssg= -github.com/cloudwego/iasm v0.2.0/go.mod h1:8rXZaNYT2n95jn+zTI1sDr+IgcD2GVs0nlbbQPiEFhY= github.com/creack/pty v1.1.9/go.mod h1:oKZEueFk5CKHvIhNR5MUki03XCEU+Q6VDXinZuGJ33E= github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38= github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c= @@ -27,8 +19,6 @@ github.com/dsnet/compress v0.0.1/go.mod h1:Aw8dCMJ7RioblQeTqt88akK31OvO8Dhf5Jflh github.com/dsnet/golib v0.0.0-20171103203638-1ea166775780/go.mod h1:Lj+Z9rebOhdfkVLjJ8T6VcRQv3SXugXy999NBtR9aFY= github.com/gabriel-vasile/mimetype v1.4.3 h1:in2uUcidCuFcDKtdcBxlR0rJ1+fsokWf+uqxgUFjbI0= github.com/gabriel-vasile/mimetype v1.4.3/go.mod h1:d8uq/6HKRL6CGdk+aubisF/M5GcPfT7nKyLpA0lbSSk= -github.com/goccy/go-json v0.10.2 h1:CrxCmQqYDkv1z7lO7Wbh2HN93uovUHgrECaO5ZrCXAU= -github.com/goccy/go-json v0.10.2/go.mod h1:6MelG93GURQebXPDq3khkgXZkazVtN9CRI+MGFi0w8I= github.com/goccy/go-json v0.10.3 h1:KZ5WoDbxAIgm2HNbYckL0se1fHD6rz5j4ywS6ebzDqA= github.com/goccy/go-json v0.10.3/go.mod h1:oq7eo15ShAhp70Anwd5lgX2pLfOS3QCiwU/PULtXL6M= github.com/goombaio/orderedmap v0.0.0-20180924084748-ba921b7e2419 h1:SajEQ6tktpF9SRIuzbiPOX9AEZZ53Bvw0k9Mzrts8Lg= @@ -39,13 +29,9 @@ github.com/k0kubun/go-ansi v0.0.0-20180517002512-3bf9e2903213/go.mod h1:vNUNkEQ1 github.com/klauspost/compress v1.4.1/go.mod h1:RyIbtBH6LamlWaDj8nUwkbUhJ87Yi3uG0guNDohfE1A= github.com/klauspost/compress v1.17.2 h1:RlWWUY/Dr4fL8qk9YG7DTZ7PDgME2V4csBXA8L/ixi4= github.com/klauspost/compress v1.17.2/go.mod h1:ntbaceVETuRiXiv4DpjP66DpAtAGkEQskQzEyD//IeE= -github.com/klauspost/cpuid v1.2.0 h1:NMpwD2G9JSFOE1/TJjGSo5zG7Yb2bTe7eq1jH+irmeE= github.com/klauspost/cpuid v1.2.0/go.mod h1:Pj4uuM528wm8OyEC2QMXAi2YiTZ96dNQPGgoMS4s3ek= -github.com/klauspost/cpuid/v2 v2.0.9 h1:lgaqFMSdTdQYdZ04uHyN2d/eKdOMyi2YLSvlQIBFYa4= -github.com/klauspost/cpuid/v2 v2.0.9/go.mod h1:FInQzS24/EEf25PyTYn52gqo7WaD8xa0213Md/qVLRg= github.com/klauspost/pgzip v1.2.6 h1:8RXeL5crjEUFnR2/Sn6GJNWtSQ3Dk8pq4CL3jvdDyjU= github.com/klauspost/pgzip v1.2.6/go.mod h1:Ch1tH69qFZu15pkjo5kYi6mth2Zzwzt50oCQKQE9RUs= -github.com/knz/go-libedit v1.10.1/go.mod h1:MZTVkCWyz0oBc7JOWP3wNAzd002ZbM/5hgShxwh4x8M= github.com/kr/pretty v0.1.0/go.mod h1:dAy3ld7l9f0ibDNOQOHHMYYIIbhfbHSm3C4ZsoJORNo= github.com/kr/pretty v0.2.1/go.mod h1:ipq/a2n7PKx3OHsz4KJII5eveXtPO4qwEXGdVfWzfnI= github.com/kr/pretty v0.3.0 h1:WgNl7dwNpEZ6jJ9k1snq4pZsg7DOEN8hP9Xw0Tsjwk0= @@ -60,8 +46,6 @@ github.com/mattn/go-runewidth v0.0.15 h1:UNAjwbU9l54TA3KzvqLGxwWjHmMgBUVhBiTjelZ github.com/mattn/go-runewidth v0.0.15/go.mod h1:Jdepj2loyihRzMpdS35Xk/zdY8IAYHsh153qUoGf23w= github.com/mitchellh/colorstring v0.0.0-20190213212951-d06e56a500db h1:62I3jR2EmQ4l5rM/4FEfDWcRD+abF5XlKShorW5LRoQ= github.com/mitchellh/colorstring v0.0.0-20190213212951-d06e56a500db/go.mod h1:l0dey0ia/Uv7NcFFVbCLtqEBQbrT4OCwCSKTEv6enCw= -github.com/montanaflynn/stats v0.7.1 h1:etflOAAHORrCC44V+aR6Ftzort912ZU+YLiSTuV8eaE= -github.com/montanaflynn/stats v0.7.1/go.mod h1:etXPPgVO6n31NxCd9KQUMvCM+ve0ruNzt6R8Bnaayow= github.com/pbnjay/memory v0.0.0-20210728143218-7b4eea64cf58 h1:onHthvaw9LFnH4t2DcNVpwGmV9E1BkGknEliJkfwQj0= github.com/pbnjay/memory v0.0.0-20210728143218-7b4eea64cf58/go.mod h1:DXv8WO4yhMYhSNPKjeNKa5WY9YCIEBRbNzFFPJbWO6Y= github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM= @@ -80,26 +64,17 @@ github.com/shopspring/decimal v1.3.1/go.mod h1:DKyhrW/HYNuLGql+MJL6WCR6knT2jwCFR github.com/sirupsen/logrus v1.9.3 h1:dueUQJ1C2q9oE3F7wvmSGAaVtTmUizReu6fjN8uqzbQ= github.com/sirupsen/logrus v1.9.3/go.mod h1:naHLuLoDiP4jHNo9R0sCBMtWGeIprob74mVsIT4qYEQ= github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME= -github.com/stretchr/objx v0.4.0/go.mod h1:YvHI0jy2hoMjB+UWwv71VJQ9isScKT/TqJzVSSt89Yw= -github.com/stretchr/objx v0.5.0/go.mod h1:Yh+to48EsGEfYuaHDzXPcE3xhTkx73EhmCGUpEOglKo= github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UVUgZn+9EI= github.com/stretchr/testify v1.7.0/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg= -github.com/stretchr/testify v1.7.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg= -github.com/stretchr/testify v1.8.0/go.mod h1:yNjHg4UonilssWZ8iaSj1OCr/vHnekPRkoO+kdMU+MU= -github.com/stretchr/testify v1.8.1/go.mod h1:w2LPCIKwWwSfY2zedu0+kehJoqGctiVI29o6fzry7u4= github.com/stretchr/testify v1.8.4 h1:CcVxjf3Q8PM0mHUKJCdn+eZZtm5yQwehR5yeSVQQcUk= github.com/stretchr/testify v1.8.4/go.mod h1:sz/lmYIOXD/1dqDmKjjqLyZ2RngseejIcXlSw2iwfAo= github.com/tevino/abool/v2 v2.1.0 h1:7w+Vf9f/5gmKT4m4qkayb33/92M+Um45F2BkHOR+L/c= github.com/tevino/abool/v2 v2.1.0/go.mod h1:+Lmlqk6bHDWHqN1cbxqhwEAwMPXgc8I1SDEamtseuXY= -github.com/twitchyliquid64/golang-asm v0.15.1 h1:SU5vSMR7hnwNxj24w34ZyCi/FmDZTkS4MhqMhdFk5YI= -github.com/twitchyliquid64/golang-asm v0.15.1/go.mod h1:a1lVb/DtPvCB8fslRZhAngC2+aY1QWCk3Cedj/Gdt08= github.com/ulikunitz/xz v0.5.6/go.mod h1:2bypXElzHzzJZwzH67Y6wb67pO62Rzfn7BSiF4ABRW8= github.com/ulikunitz/xz v0.5.11 h1:kpFauv27b6ynzBNT/Xy+1k+fK4WswhN/6PN5WhFAGw8= github.com/ulikunitz/xz v0.5.11/go.mod h1:nbz6k7qbPmH4IRqmfOplQw/tblSgqTqBwxkY0oWt/14= github.com/yuin/gopher-lua v1.1.1 h1:kYKnWBjvbNP4XLT3+bPEwAXJx262OhaHDWDVOPjL46M= github.com/yuin/gopher-lua v1.1.1/go.mod h1:GBR0iDaNXjAgGg9zfCvksxSRnQx76gclCIb7kdAd1Pw= -golang.org/x/arch v0.0.0-20210923205945-b76863e36670 h1:18EFjUmQOcUvxNYSkA6jO9VAiXCnxFY6NyDX0bHDmkU= -golang.org/x/arch v0.0.0-20210923205945-b76863e36670/go.mod h1:5om86z9Hs0C8fWVUuoMHwpExlXzs5Tkyp9hOrfG7pp8= golang.org/x/exp v0.0.0-20231006140011-7918f672742d h1:jtJma62tbqLibJ5sFQz8bKtEM8rJBtfilJ2qTU199MI= golang.org/x/exp v0.0.0-20231006140011-7918f672742d/go.mod h1:ldy0pHrwJyGW56pPQzzkH36rKxoZW1tw7ZJpeKx+hdo= golang.org/x/net v0.17.0 h1:pVaXccu2ozPjCXewfr1S7xza/zcXTity9cCdXQYSjIM= @@ -122,8 +97,6 @@ gopkg.in/errgo.v2 v2.1.0/go.mod h1:hNsd1EY+bozCKY1Ytp96fpM3vjJbqLJn88ws8XvfDNI= gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM= gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA= gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM= -nullprogram.com/x/optparse v1.0.0/go.mod h1:KdyPE+Igbe0jQUrVfMqDMeJQIJZEuyV7pjYmp6pbG50= -rsc.io/pdf v0.1.1/go.mod h1:n8OzWcQ6Sp37PL01nO98y4iUCRdTGarVfzxY20ICaU4= scientificgo.org/special v0.0.0 h1:P6WJkECo6tgtvZAEfNXl+KEB9ReAatjKAeX8U07mjSc= scientificgo.org/special v0.0.0/go.mod h1:LoGVh9tS431RLTJo7gFlYDKFWq44cEb7QqL+M0EKtZU= scientificgo.org/testutil v0.0.0 h1:y356DHRo0tAz9zIFmxlhZoKDlHPHaWW/DCm9k3PhIMA= diff --git a/pkg/obiformats/fastqseq_read.go b/pkg/obiformats/fastqseq_read.go index 85f8088..fe11869 100644 --- a/pkg/obiformats/fastqseq_read.go +++ b/pkg/obiformats/fastqseq_read.go @@ -17,6 +17,7 @@ import ( func EndOfLastFastqEntry(buffer []byte) int { var i int + // log.Warnf("EndOfLastFastqEntry(%d): %s", len(buffer), string(buffer[0:20])) imax := len(buffer) state := 0 restart := imax - 1 @@ -32,39 +33,48 @@ func EndOfLastFastqEntry(buffer []byte) int { case 0: if C == '+' { // Potential start of quality part step 1 + // log.Warn("Potential start of quality part step 1 - +") state = 1 restart = i } case 1: if is_end_of_line { // Potential start of quality part step 2 + // log.Warn("Potential start of quality part step 2 - +/end of line") state = 2 } else { // it was not the start of quality part + // log.Warn("it was not the start of quality part") state = 0 i = restart } case 2: if is_sep { // Potential start of quality part step 2 (stay in the same state) + // log.Warn("Potential start of quality part step 2 - skipping separator") state = 2 } else if (C >= 'a' && C <= 'z') || (C >= 'A' && C <= 'Z') || C == '-' || C == '.' || C == '[' || C == ']' { - // End of the sequence + // progressing along of the sequence + // log.Warn("Detected the end of the sequence switching to state 3") state = 3 } else { // it was not the start of quality part + // log.Warn("it was not the start of quality part because is not preceded by sequence") state = 0 i = restart } case 3: if is_end_of_line { // Entrering in the header line + // log.Warn("Potentially entrering in the header line") state = 4 } else if (C >= 'a' && C <= 'z') || (C >= 'A' && C <= 'Z') || C == '-' || C == '.' || C == '[' || C == ']' { // progressing along of the sequence + // log.Warn("Progressing along of the sequence") state = 3 } else { // it was not the sequence part + // log.Warnf("it was not the sequence part : %c", C) state = 0 i = restart } @@ -72,6 +82,7 @@ func EndOfLastFastqEntry(buffer []byte) int { if is_end_of_line { state = 4 } else { + state = 5 } case 5: @@ -80,15 +91,18 @@ func EndOfLastFastqEntry(buffer []byte) int { state = 0 i = restart } else if C == '@' { + // It was the header line + // log.Warn("It was the header line") state = 6 cut = i } case 6: if is_end_of_line { + // log.Warn("====> End of the last sequence") state = 7 } else { - state = 0 - i = restart + // log.Warnf("%s: Strange it was not the end of the last sequence : %c : %s", string(buffer[0:40]), C, string(buffer[i-20:i+5])) + state = 5 } } } diff --git a/pkg/obiformats/seqfile_chunk_read.go b/pkg/obiformats/seqfile_chunk_read.go index 727325f..b729829 100644 --- a/pkg/obiformats/seqfile_chunk_read.go +++ b/pkg/obiformats/seqfile_chunk_read.go @@ -76,6 +76,8 @@ func ReadSeqFileChunk( extbuff := buff[l:(l + fileChunkSize - 1)] size, err = io.ReadFull(reader, extbuff) buff = buff[0:(l + size)] + // log.Warnf("Splitter not found, attempting %d to read in %d B increments : len(buff) = %d/%d", ic, fileChunkSize, len(extbuff), len(buff)) + } fullbuff = buff diff --git a/pkg/obioptions/version.go b/pkg/obioptions/version.go index 956df64..842ea9c 100644 --- a/pkg/obioptions/version.go +++ b/pkg/obioptions/version.go @@ -7,7 +7,7 @@ import ( // TODO: The version number is extracted from git. This induces that the version // corresponds to the last commit, and not the one when the file will be // commited -var _Commit = "b37fc39" +var _Commit = "74280e4" var _Version = "Release 4.2.0" // Version returns the version of the obitools package.