Merge pull request github#11175 from erik-krogh/erb

JS: extract .erb files as html

Author: erik-krogh

javascript/extractor/src/com/semmle/js/extractor/AutoBuild.java

@@ -141,7 +141,7 @@
  *   <li>All JavaScript files, that is, files with one of the extensions supported by {@link
  *       FileType#JS} (currently ".js", ".jsx", ".mjs", ".cjs", ".es6", ".es").
  *   <li>All HTML files, that is, files with with one of the extensions supported by {@link
- *       FileType#HTML} (currently ".htm", ".html", ".xhtm", ".xhtml", ".vue").
+ *       FileType#HTML} (currently ".htm", ".html", ".xhtm", ".xhtml", ".vue", ".html.erb").
  *   <li>All YAML files, that is, files with one of the extensions supported by {@link
  *       FileType#YAML} (currently ".raml", ".yaml", ".yml").
  *   <li>Files with base name "package.json" or "tsconfig.json", and files whose base name

javascript/extractor/src/com/semmle/js/extractor/FileExtractor.java

@@ -104,7 +104,7 @@ private static int skipBOM(byte[] bytes, int length) {
 
   /** Information about supported file types. */
   public static enum FileType {
-    HTML(".htm", ".html", ".xhtm", ".xhtml", ".vue", ".hbs", ".ejs", ".njk") {
+    HTML(".htm", ".html", ".xhtm", ".xhtml", ".vue", ".hbs", ".ejs", ".njk", ".html.erb") {
       @Override
       public IExtractor mkExtractor(ExtractorConfig config, ExtractorState state) {
         return new HTMLExtractor(config, state);

javascript/extractor/src/com/semmle/js/extractor/Main.java

@@ -41,7 +41,7 @@ public class Main {
    * A version identifier that should be updated every time the extractor changes in such a way that
    * it may produce different tuples for the same file under the same {@link ExtractorConfig}.
    */
-  public static final String EXTRACTOR_VERSION = "2022-11-14";
+  public static final String EXTRACTOR_VERSION = "2022-11-15";
 
   public static final Pattern NEWLINE = Pattern.compile("\n");
 

javascript/extractor/tests/vue/input/rails.html.erb

@@ -0,0 +1,3 @@
+<script>
+  console.log("FOO");
+</script>

javascript/extractor/tests/vue/output/trap/rails.html.erb.trap

@@ -0,0 +1,137 @@
+#10000=@"/rails.erb;sourcefile"
+files(#10000,"/rails.erb")
+#10001=@"/;folder"
+folders(#10001,"/")
+containerparent(#10001,#10000)
+#10002=@"loc,{#10000},0,0,0,0"
+locations_default(#10002,#10000,0,0,0,0)
+hasLocation(#10000,#10002)
+#20000=@"global_scope"
+scopes(#20000,0)
+#20001=*
+#20002=@"script;{#10000},1,9"
+#20003=*
+lines(#20003,#20002,"","
+")
+#20004=@"loc,{#10000},1,9,1,8"
+locations_default(#20004,#10000,1,9,1,8)
+hasLocation(#20003,#20004)
+#20005=*
+lines(#20005,#20002,"  console.log(""FOO"");","
+")
+#20006=@"loc,{#10000},2,1,2,21"
+locations_default(#20006,#10000,2,1,2,21)
+hasLocation(#20005,#20006)
+indentation(#10000,2," ",2)
+numlines(#20002,2,1,0)
+#20007=*
+tokeninfo(#20007,6,#20002,0,"console")
+#20008=@"loc,{#10000},2,3,2,9"
+locations_default(#20008,#10000,2,3,2,9)
+hasLocation(#20007,#20008)
+#20009=*
+tokeninfo(#20009,8,#20002,1,".")
+#20010=@"loc,{#10000},2,10,2,10"
+locations_default(#20010,#10000,2,10,2,10)
+hasLocation(#20009,#20010)
+#20011=*
+tokeninfo(#20011,6,#20002,2,"log")
+#20012=@"loc,{#10000},2,11,2,13"
+locations_default(#20012,#10000,2,11,2,13)
+hasLocation(#20011,#20012)
+#20013=*
+tokeninfo(#20013,8,#20002,3,"(")
+#20014=@"loc,{#10000},2,14,2,14"
+locations_default(#20014,#10000,2,14,2,14)
+hasLocation(#20013,#20014)
+#20015=*
+tokeninfo(#20015,4,#20002,4,"""FOO""")
+#20016=@"loc,{#10000},2,15,2,19"
+locations_default(#20016,#10000,2,15,2,19)
+hasLocation(#20015,#20016)
+#20017=*
+tokeninfo(#20017,8,#20002,5,")")
+#20018=@"loc,{#10000},2,20,2,20"
+locations_default(#20018,#10000,2,20,2,20)
+hasLocation(#20017,#20018)
+#20019=*
+tokeninfo(#20019,8,#20002,6,";")
+#20020=@"loc,{#10000},2,21,2,21"
+locations_default(#20020,#10000,2,21,2,21)
+hasLocation(#20019,#20020)
+#20021=*
+tokeninfo(#20021,0,#20002,7,"")
+#20022=@"loc,{#10000},3,1,3,0"
+locations_default(#20022,#10000,3,1,3,0)
+hasLocation(#20021,#20022)
+toplevels(#20002,1)
+#20023=@"loc,{#10000},1,9,3,0"
+locations_default(#20023,#10000,1,9,3,0)
+hasLocation(#20002,#20023)
+#20024=*
+stmts(#20024,2,#20002,0,"console.log(""FOO"");")
+#20025=@"loc,{#10000},2,3,2,21"
+locations_default(#20025,#10000,2,3,2,21)
+hasLocation(#20024,#20025)
+stmt_containers(#20024,#20002)
+#20026=*
+exprs(#20026,13,#20024,0,"console.log(""FOO"")")
+#20027=@"loc,{#10000},2,3,2,20"
+locations_default(#20027,#10000,2,3,2,20)
+hasLocation(#20026,#20027)
+enclosing_stmt(#20026,#20024)
+expr_containers(#20026,#20002)
+#20028=*
+exprs(#20028,14,#20026,-1,"console.log")
+#20029=@"loc,{#10000},2,3,2,13"
+locations_default(#20029,#10000,2,3,2,13)
+hasLocation(#20028,#20029)
+enclosing_stmt(#20028,#20024)
+expr_containers(#20028,#20002)
+#20030=*
+exprs(#20030,79,#20028,0,"console")
+hasLocation(#20030,#20008)
+enclosing_stmt(#20030,#20024)
+expr_containers(#20030,#20002)
+literals("console","console",#20030)
+#20031=@"var;{console};{#20000}"
+variables(#20031,"console",#20000)
+bind(#20030,#20031)
+#20032=*
+exprs(#20032,0,#20028,1,"log")
+hasLocation(#20032,#20012)
+enclosing_stmt(#20032,#20024)
+expr_containers(#20032,#20002)
+literals("log","log",#20032)
+#20033=*
+exprs(#20033,4,#20026,0,"""FOO""")
+hasLocation(#20033,#20016)
+enclosing_stmt(#20033,#20024)
+expr_containers(#20033,#20002)
+literals("FOO","""FOO""",#20033)
+#20034=*
+regexpterm(#20034,14,#20033,0,"FOO")
+#20035=@"loc,{#10000},2,16,2,18"
+locations_default(#20035,#10000,2,16,2,18)
+hasLocation(#20034,#20035)
+regexp_const_value(#20034,"FOO")
+#20036=*
+entry_cfg_node(#20036,#20002)
+hasLocation(#20036,#20004)
+#20037=*
+exit_cfg_node(#20037,#20002)
+hasLocation(#20037,#20022)
+successor(#20024,#20030)
+successor(#20033,#20026)
+successor(#20032,#20028)
+successor(#20030,#20032)
+successor(#20028,#20033)
+successor(#20026,#20037)
+successor(#20036,#20024)
+toplevel_parent_xml_node(#20002,#20001)
+xmlElements(#20001,"script",#10000,0,#10000)
+#20038=@"loc,{#10000},1,1,3,9"
+locations_default(#20038,#10000,1,1,3,9)
+xmllocations(#20001,#20038)
+numlines(#10000,3,1,0)
+filetype(#10000,"html")