Fix #475 - SkipTo used incorrect storage of ignore expressions, would match the target expression if present within an ignorable

3 files changed, 27 insertions, 11 deletions

diff --git a/CHANGES b/CHANGES
index fd210a5..2886034 100644
--- a/CHANGES
+++ b/CHANGES
@@ -4,6 +4,10 @@ Change Log
 
 Version 3.1.0a2 - (in development)
 ----------------------------------
+Fixed bug in `SkipTo` where ignore expressions were not properly handled while
+scanning for the target expression. Issue #475, reported by elkniwt, thanks
+(this bug has been there for a looooong time!).
+
 Updated ci.yml permissions to limit default access to source - submitted by Joyce
 Brum of Google. Thanks so much!
 
diff --git a/pyparsing/core.py b/pyparsing/core.py
index 02ae50a..b51779f 100644
--- a/pyparsing/core.py
+++ b/pyparsing/core.py
@@ -5281,7 +5281,8 @@ class SkipTo(ParseElementEnhance):
     ):
         super().__init__(other)
         failOn = failOn or fail_on
-        self.ignoreExpr = ignore
+        if ignore is not None:
+            self.ignore(ignore)
         self.mayReturnEmpty = True
         self.mayIndexError = False
         self.includeMatch = include
@@ -5299,9 +5300,7 @@ class SkipTo(ParseElementEnhance):
         self_failOn_canParseNext = (
             self.failOn.canParseNext if self.failOn is not None else None
         )
-        self_ignoreExpr_tryParse = (
-            self.ignoreExpr.try_parse if self.ignoreExpr is not None else None
-        )
+        self_preParse = self.preParse if self.callPreparse else None
 
         tmploc = loc
         while tmploc <= instrlen:
@@ -5310,13 +5309,9 @@ class SkipTo(ParseElementEnhance):
                 if self_failOn_canParseNext(instring, tmploc):
                     break
 
-            if self_ignoreExpr_tryParse is not None:
-                # advance past ignore expressions
-                while 1:
-                    try:
-                        tmploc = self_ignoreExpr_tryParse(instring, tmploc)
-                    except ParseBaseException:
-                        break
+            if self_preParse is not None:
+                # skip grammar-ignored expressions
+                tmploc = self_preParse(instring, tmploc)
 
             try:
                 self_expr_parse(instring, tmploc, doActions=False, callPreParse=False)
diff --git a/tests/test_unit.py b/tests/test_unit.py
index c2a7160..0f1cb5a 100644
--- a/tests/test_unit.py
+++ b/tests/test_unit.py
@@ -1692,6 +1692,23 @@ class Test02_WithoutPackrat(ppt.TestParseResultsAsserts, TestCase):
             {"_skipped": ["red ", "456 "]},
         )
 
+    def testSkipToPreParseIgnoreExprs(self):
+        # added to verify fix to Issue #475
+        from pyparsing import Word, alphanums, python_style_comment
+
+        some_grammar = Word(alphanums) + ":=" + ... + ';'
+        some_grammar.ignore(python_style_comment)
+        try:
+            result = some_grammar.parse_string("""\
+                var1 := 2 # 3; <== this semi-colon will match!
+                      + 1;
+                """, parse_all=True)
+        except ParseException as pe:
+            print(pe.explain())
+            raise
+        else:
+            print(result.dump())
+
     def testEllipsisRepetition(self):
 
         word = pp.Word(pp.alphas).setName("word")