Merge pull request #5721 from overleaf/hb-fix-log-line-parsing

Improve file line error log parser regex

GitOrigin-RevId: d3fbb39b4a6d99e339c1d6e6eb81d9cfb3ec5935

services/web/frontend/js/ide/log-parser/latex-log-parser.js

@@ -7,6 +7,7 @@ const PACKAGE_WARNING_REGEX = /^(Package \b.+\b Warning:.*)$/
 const LINES_REGEX = /lines? ([0-9]+)/
 // This is used to parse the package name from the package warnings
 const PACKAGE_REGEX = /^Package (\b.+\b) Warning/
+const FILE_LINE_ERROR_REGEX = /^([./].*):(\d+): (.*)/
 
 const STATE = {
   NORMAL: 0,
@@ -83,7 +84,7 @@ export default class LatexParser {
   }
 
   currentLineIsFileLineError() {
-    return /^\/.*:\d+: .*/.test(this.currentLine)
+    return FILE_LINE_ERROR_REGEX.test(this.currentLine)
   }
 
   currentLineIsRunawayArgument() {
@@ -103,7 +104,7 @@ export default class LatexParser {
   }
 
   parseFileLineError() {
-    const result = this.currentLine.match(/^(\/.*):(\d+): (.*)/)
+    const result = this.currentLine.match(FILE_LINE_ERROR_REGEX)
     this.currentError = {
       line: result[2],
       file: result[1],

services/web/test/frontend/helpers/fixtures/logs/file-line-error-2.log

@@ -0,0 +1,105 @@
+This is pdfTeX, Version 3.141592653-2.6-1.40.23 (TeX Live 2021) (preloaded format=pdflatex 2021.9.30)  9 NOV 2021 16:55
+entering extended mode
+ \write18 enabled.
+ %&-line parsing enabled.
+**main.tex
+(./main.tex
+LaTeX2e <2021-06-01> patch level 1
+L3 programming layer <2021-07-12> (/usr/local/texlive/2021/texmf-dist/tex/latex
+/base/article.cls
+Document Class: article 2021/02/12 v1.4n Standard LaTeX document class
+(/usr/local/texlive/2021/texmf-dist/tex/latex/base/size10.clo
+File: size10.clo 2021/02/12 v1.4n Standard LaTeX file (size option)
+)
+\c@part=\count182
+\c@section=\count183
+\c@subsection=\count184
+\c@subsubsection=\count185
+\c@paragraph=\count186
+\c@subparagraph=\count187
+\c@figure=\count188
+\c@table=\count189
+\abovecaptionskip=\skip47
+\belowcaptionskip=\skip48
+\bibindent=\dimen138
+) (/usr/local/texlive/2021/texmf-dist/tex/latex/base/inputenc.sty
+Package: inputenc 2021/02/14 v1.3d Input encoding file
+\inpenc@prehook=\toks16
+\inpenc@posthook=\toks17
+) (/usr/local/texlive/2021/texmf-dist/tex/latex/l3backend/l3backend-pdftex.def
+File: l3backend-pdftex.def 2021-07-12 L3 backend support: PDF output (pdfTeX)
+\l__color_backend_stack_int=\count190
+\l__pdf_internal_box=\box50
+) (./output.aux (./acks/name.aux))
+\openout1 = `output.aux'.
+
+LaTeX Font Info:    Checking defaults for OML/cmm/m/it on input line 8.
+LaTeX Font Info:    ... okay on input line 8.
+LaTeX Font Info:    Checking defaults for OMS/cmsy/m/n on input line 8.
+LaTeX Font Info:    ... okay on input line 8.
+LaTeX Font Info:    Checking defaults for OT1/cmr/m/n on input line 8.
+LaTeX Font Info:    ... okay on input line 8.
+LaTeX Font Info:    Checking defaults for T1/cmr/m/n on input line 8.
+LaTeX Font Info:    ... okay on input line 8.
+LaTeX Font Info:    Checking defaults for TS1/cmr/m/n on input line 8.
+LaTeX Font Info:    ... okay on input line 8.
+LaTeX Font Info:    Checking defaults for OMX/cmex/m/n on input line 8.
+LaTeX Font Info:    ... okay on input line 8.
+LaTeX Font Info:    Checking defaults for U/cmr/m/n on input line 8.
+LaTeX Font Info:    ... okay on input line 8.
+LaTeX Font Info:    External font `cmex10' loaded for size
+(Font)              <12> on input line 10.
+LaTeX Font Info:    External font `cmex10' loaded for size
+(Font)              <8> on input line 10.
+LaTeX Font Info:    External font `cmex10' loaded for size
+(Font)              <6> on input line 10.
+[1
+
+{/usr/local/texlive/2021/texmf-var/fonts/map/pdftex/updmap/pdftex.map}]
+\openout2 = `acks/name.aux'.
+
+(./acks/name.tex
+! Misplaced alignment tab character &.
+l.1 inserting an ampersand &
+                            
+I can't figure out why you would want to use a tab mark
+here. If you just want an ampersand, the remedy is
+simple: Just type `I\&' now. But if some right brace
+up above has ended a previous alignment prematurely,
+you're probably due for more error messages, and you
+might try typing `S' now just to see what is salvageable.
+
+) [2
+
+]
+! Misplaced alignment tab character &.
+l.14 &
+      
+I can't figure out why you would want to use a tab mark
+here. If you just want an ampersand, the remedy is
+simple: Just type `I\&' now. But if some right brace
+up above has ended a previous alignment prematurely,
+you're probably due for more error messages, and you
+might try typing `S' now just to see what is salvageable.
+
+(./output.aux (./acks/name.aux)) ) 
+Here is how much of TeX's memory you used:
+ 450 strings out of 478542
+ 7915 string characters out of 5850413
+ 299724 words of memory out of 5000000
+ 18449 multiletter control sequences out of 15000+600000
+ 407070 words of font info for 39 fonts, out of 8000000 for 9000
+ 1141 hyphenation exceptions out of 8191
+ 34i,6n,41p,150b,191s stack positions out of 5000i,500n,10000p,200000b,80000s
+</usr/local/texlive/2021/texmf-dist/fonts/typ
+e1/public/amsfonts/cm/cmbx12.pfb></usr/local/texlive/2021/texmf-dist/fonts/type
+1/public/amsfonts/cm/cmr10.pfb></usr/local/texlive/2021/texmf-dist/fonts/type1/
+public/amsfonts/cm/cmr12.pfb></usr/local/texlive/2021/texmf-dist/fonts/type1/pu
+blic/amsfonts/cm/cmr17.pfb>
+Output written on output.pdf (2 pages, 42045 bytes).
+PDF statistics:
+ 31 PDF objects out of 1000 (max. 8388607)
+ 18 compressed objects within 1 object stream
+ 0 named destinations out of 1000 (max. 500000)
+ 1 words of extra memory for PDF output out of 10000 (max. 10000000)
+

services/web/test/frontend/ide/log-parser/logParserTests.js

@@ -77,6 +77,13 @@ describe('logParser', function (done) {
         flag: 'r',
       }
     )
+    this.secondaryFileLineErrorLog = fs.readFileSync(
+      path.resolve(__dirname, fixturePath + 'file-line-error-2.log'),
+      {
+        encoding: 'utf8',
+        flag: 'r',
+      }
+    )
   })
 
   it('should parse errors', function () {
@@ -401,10 +408,10 @@ describe('logParser', function (done) {
   })
 
   it('should perform file line error parsing', function () {
-    const latexParser = new LatexLogParser(this.fileLineErrorLog)
-    const errors = latexParser.parse().errors
+    let latexParser = new LatexLogParser(this.fileLineErrorLog)
+    let errors = latexParser.parse().errors
 
-    const expectedErrors = [
+    let expectedErrors = [
       [
         1,
         'Undefined control sequence.',
@@ -418,6 +425,25 @@ describe('logParser', function (done) {
         [errors[i].line, errors[i].message, errors[i].file] + ''
       )
     }
+
+    // again with a more complex example
+
+    latexParser = new LatexLogParser(this.secondaryFileLineErrorLog)
+    errors = latexParser.parse().errors
+
+    expectedErrors = [
+      [1, 'Misplaced alignment tab character &.', './acks/name.tex'],
+      [14, 'Misplaced alignment tab character &.', './main.tex'],
+    ]
+
+    expect(errors.length).to.equal(expectedErrors.length)
+    for (let i = 0; i < errors.length; i++) {
+      expect(expectedErrors[i]).to.deep.equal([
+        errors[i].line,
+        errors[i].message,
+        errors[i].file,
+      ])
+    }
   })
 
   it('should ignore duplicates', function () {