JS: classify Doxygen-generated files as "generated"

esbena · esbena · commit 7f55e3f336ff · 2019-11-04T09:57:41.000+01:00
diff --git a/change-notes/1.23/analysis-javascript.md b/change-notes/1.23/analysis-javascript.md
@@ -14,6 +14,7 @@
 
 * TypeScript 3.6 features are supported.
 
+* Automatic classification of generated files has been improved, in particular files generated by Doxygen are now recognized.
 
 ## New queries
 
diff --git a/javascript/ql/src/semmle/javascript/GeneratedCode.qll b/javascript/ql/src/semmle/javascript/GeneratedCode.qll
@@ -137,6 +137,11 @@ private predicate isGeneratedHtml(File f) {
     e.getAttributeByName("name").getValue() = "generator"
   )
   or
+  exists(HTML::CommentNode comment |
+    comment.getText().regexpMatch("\\s*Generated by [\\w-]+ \\d+\\.\\d+\\.\\d+\\s*") and
+    comment.getFile() = f
+  )
+  or
   20 < countStartingHtmlElements(f, _)
 }
 
diff --git a/javascript/ql/test/query-tests/filters/ClassifyFiles/ClassifyFiles.expected b/javascript/ql/test/query-tests/filters/ClassifyFiles/ClassifyFiles.expected
@@ -6,6 +6,7 @@
 | ai.1.2.3-build0123.js:0:0:0:0 | ai.1.2.3-build0123.js | library |
 | bundle-directive.js:0:0:0:0 | bundle-directive.js | generated |
 | data.js:0:0:0:0 | data.js | generated |
+| doxygen-generated.html:0:0:0:0 | doxygen-generated.html | generated |
 | etherpad.html:0:0:0:0 | etherpad.html | generated |
 | exported-data.js:0:0:0:0 | exported-data.js | generated |
 | htmltidy.html:0:0:0:0 | htmltidy.html | generated |
diff --git a/javascript/ql/test/query-tests/filters/ClassifyFiles/doxygen-generated.html b/javascript/ql/test/query-tests/filters/ClassifyFiles/doxygen-generated.html

Original file line number	Diff line number	Diff line change
`@@ -14,6 +14,7 @@`
`14`	`14`
`15`	`15`	`* TypeScript 3.6 features are supported.`
`16`	`16`
	`17`	`+* Automatic classification of generated files has been improved, in particular files generated by Doxygen are now recognized.`
`17`	`18`
`18`	`19`	`## New queries`
`19`	`20`
Original file line number	Diff line number	Diff line change
`@@ -137,6 +137,11 @@ private predicate isGeneratedHtml(File f) {`
`137`	`137`	`e.getAttributeByName("name").getValue() = "generator"`
`138`	`138`	`)`
`139`	`139`	`or`
	`140`	`+ exists(HTML::CommentNode comment \|`
	`141`	`+ comment.getText().regexpMatch("\\sGenerated by [\\w-]+ \\d+\\.\\d+\\.\\d+\\s") and`
	`142`	`+ comment.getFile() = f`
	`143`	`+ )`
	`144`	`+ or`
`140`	`145`	`20 < countStartingHtmlElements(f, _)`
`141`	`146`	`}`
`142`	`147`