Added python_quoted_string; fixed exception messages for ParseElement…

…Enhance subclasses

CHANGES

@@ -28,14 +28,18 @@ help from Devin J. Pohly in structuring the code to enable this peaceful transit
 
   Suggested by Antony Lee (issue #412), PR (#413) by Devin J. Pohly.
 
+- Added new builtin `python_quoted_string`, which will match any form
+  of single-line or multiline quoted strings defined in Python. (Inspired
+  by discussion with Andreas Schörgenhumer in Issue #421.)
+
 - Fixed bug in `Word` when `max=2`. Also added performance enhancement
   when specifying `exact` argument. Reported in issue #409 by
   panda-34, nice catch!
 
 - `Word` arguments are now validated if `min` and `max` are both
   given, that `min` <= `max`; raises `ValueError` if values are invalid.
 
-- Extended `expr[]` notation for repetition of expr to accept a
+- Extended `expr[]` notation for repetition of `expr` to accept a
   slice, where the slice's stop value indicates a `stop_on`
   expression:
 
@@ -62,6 +66,9 @@ help from Devin J. Pohly in structuring the code to enable this peaceful transit
 - Fixed bug in srange, when parsing escaped '/' and '\' inside a
   range set.
 
+- Fixed exception messages for some ParserElements with custom names,
+  which instead showed their contained expression names.
+
 - Multiple added and corrected type annotations. With much help from
   Stephen Rosen, thanks!
 

docs/HowToUsePyparsing.rst

@@ -6,7 +6,7 @@ Using the pyparsing module
 :address: ptmcg.pm+pyparsing@gmail.com
 
 :revision: 3.0.10
-:date: May, 2022
+:date: July, 2022
 
 :copyright: Copyright |copy| 2003-2022 Paul McGuire.
 
@@ -1308,6 +1308,8 @@ Common string and token constants
 
 - ``quoted_string`` - ``sgl_quoted_string | dbl_quoted_string``
 
+- ``python_quoted_string`` - ``quoted_string | multiline quoted string``
+
 - ``c_style_comment`` - a comment block delimited by ``'/*'`` and ``'*/'`` sequences; can span
   multiple lines, but does not support nesting of comments
 

pyparsing/__init__.py

@@ -121,7 +121,7 @@ def __repr__(self):
 
 
 __version_info__ = version_info(3, 0, 10, "final", 0)
-__version_time__ = "24 Jun 2022 16:29 UTC"
+__version_time__ = "29 Jun 2022 06:57 UTC"
 __version__ = __version_info__.__version__
 __versionTime__ = __version_time__
 __author__ = "Paul McGuire <ptmcg.gm+pyparsing@gmail.com>"

pyparsing/core.py

@@ -4446,7 +4446,11 @@ def recurse(self) -> Sequence[ParserElement]:
 
     def parseImpl(self, instring, loc, doActions=True):
         if self.expr is not None:
-            return self.expr._parse(instring, loc, doActions, callPreParse=False)
+            try:
+                return self.expr._parse(instring, loc, doActions, callPreParse=False)
+            except ParseBaseException as pbe:
+                pbe.msg = self.errmsg
+                raise
         else:
             raise ParseException(instring, loc, "No expression defined", self)
 
@@ -5870,10 +5874,29 @@ def autoname_elements() -> None:
 ).set_name("string enclosed in single quotes")
 
 quoted_string = Combine(
-    Regex(r'"(?:[^"\n\r\\]|(?:"")|(?:\\(?:[^x]|x[0-9a-fA-F]+)))*') + '"'
-    | Regex(r"'(?:[^'\n\r\\]|(?:'')|(?:\\(?:[^x]|x[0-9a-fA-F]+)))*") + "'"
+    (Regex(r'"(?:[^"\n\r\\]|(?:"")|(?:\\(?:[^x]|x[0-9a-fA-F]+)))*') + '"').set_name(
+        "double quoted string"
+    )
+    | (Regex(r"'(?:[^'\n\r\\]|(?:'')|(?:\\(?:[^x]|x[0-9a-fA-F]+)))*") + "'").set_name(
+        "single quoted string"
+    )
 ).set_name("quoted string using single or double quotes")
 
+python_quoted_string = Combine(
+    (Regex(r'"([^"]|""?(?!"))*', flags=re.MULTILINE) + '"""').set_name(
+        "multiline double quoted string"
+    )
+    | (Regex(r"'([^']|''?(?!'))*", flags=re.MULTILINE) + "'''").set_name(
+        "multiline single quoted string"
+    )
+    | (Regex(r'"(?:[^"\n\r\\]|(?:"")|(?:\\(?:[^x]|x[0-9a-fA-F]+)))*') + '"').set_name(
+        "double quoted string"
+    )
+    | (Regex(r"'(?:[^'\n\r\\]|(?:'')|(?:\\(?:[^x]|x[0-9a-fA-F]+)))*") + "'").set_name(
+        "single quoted string"
+    )
+).set_name("Python quoted string")
+
 unicode_string = Combine("u" + quoted_string.copy()).set_name("unicode string literal")
 
 

pyparsing/exceptions.py

@@ -80,7 +80,9 @@ def explain_exception(exc, depth=16):
 
                 f_self = frm.f_locals.get("self", None)
                 if isinstance(f_self, ParserElement):
-                    if not frm.f_code.co_name.startswith(("parseImpl", "_parseNoCache")):
+                    if not frm.f_code.co_name.startswith(
+                        ("parseImpl", "_parseNoCache")
+                    ):
                         continue
                     if id(f_self) in seen:
                         continue

tests/test_diagram.py

@@ -70,11 +70,11 @@ def test_json(self):
 
     def test_sql(self):
         railroad = self.generate_railroad(simpleSQL, "simpleSQL")
-        assert len(railroad) == 18
+        assert len(railroad) == 20
         railroad = self.generate_railroad(
             simpleSQL, "simpleSQL", show_results_names=True
         )
-        assert len(railroad) == 18
+        assert len(railroad) == 20
 
     def test_calendars(self):
         railroad = self.generate_railroad(calendars, "calendars")