ssc_codegen 0.7.3__tar.gz → 0.7.4__tar.gz

{ssc_codegen-0.7.3 → ssc_codegen-0.7.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ssc_codegen
-Version: 0.7.3
+Version: 0.7.4
 Summary: Python-dsl code converter to html parser for web scraping 
 Project-URL: Documentation, https://github.com/vypivshiy/selector_schema_codegen#readme
 Project-URL: Issues, https://github.com/vypivshiy/selector_schema_codegen/issues

{ssc_codegen-0.7.3 → ssc_codegen-0.7.4}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "ssc_codegen"
-version = "0.7.3"
+version = "0.7.4"
 description = "Python-dsl code converter to html parser for web scraping "
 readme = "README.md"
 requires-python = ">=3.10"
@@ -13,6 +13,7 @@ dependencies = [
     "typer>=0.15.1",
     "typing_extensions;python_version<'3.11'",
 ]
+
 classifiers = [
     "Development Status :: 3 - Alpha",
     "Environment :: Console",

{ssc_codegen-0.7.3 → ssc_codegen-0.7.4}/ssc_codegen/__init__.py

@@ -3,7 +3,7 @@ from .document import HTMLDocument, StringDocument, ArrayDocument, AssertDocumen
 from .json_struct import Json
 from .schema import ItemSchema, DictSchema, ListSchema, FlatListSchema
 
-VERSION = "0.7.3"
+VERSION = "0.7.4"
 
 class __MISSING(object):
     pass

{ssc_codegen-0.7.3 → ssc_codegen-0.7.4}/ssc_codegen/document.py

@@ -1,6 +1,6 @@
 """high-level AST builder interface"""
 
-from typing import Type
+from typing import Type, Pattern
 
 from typing_extensions import Self
 
@@ -51,7 +51,7 @@ from .ast_ssc import (
     ToBool,
     ArrayLengthExpression,
 )
-from .document_utlis import assert_re_expression
+from .document_utlis import assert_re_expression, unverbosify_regex
 from .schema import BaseSchema
 from .selector_utils import validate_css_query, validate_xpath_query
 from .tokens import VariableType
@@ -458,7 +458,7 @@ class StringDocument(BaseDocument):
                 )
         return self
 
-    def re(self, pattern: str, group: int = 1) -> Self:
+    def re(self, pattern: str | Pattern, group: int = 1) -> Self:
         """extract first regex result.
 
         NOTE:
@@ -466,6 +466,7 @@ class StringDocument(BaseDocument):
 
         - accept STRING, return STRING
         """
+        pattern = unverbosify_regex(pattern)
         assert_re_expression(pattern)
 
         if self.stack_last_ret != VariableType.STRING:
@@ -475,11 +476,12 @@ class StringDocument(BaseDocument):
         self._add(RegexExpression(pattern=pattern, group=group))
         return self
 
-    def re_all(self, pattern: str) -> Self:
+    def re_all(self, pattern: str | Pattern) -> Self:
         """extract all regex results.
 
         - accept STRING, return LIST_STRING
         """
+        pattern = unverbosify_regex(pattern)
         assert_re_expression(pattern, max_groups=1)
         if self.stack_last_ret != VariableType.STRING:
             self._raise_wrong_type_error(
@@ -488,12 +490,13 @@ class StringDocument(BaseDocument):
         self._add(RegexAllExpression(pattern=pattern))
         return self
 
-    def re_sub(self, pattern: str, repl: str = "") -> Self:
+    def re_sub(self, pattern: str | Pattern, repl: str = "") -> Self:
         """Replace substring by `pattern` to `repl`.
 
         - accept STRING, return STRING
         - accept LIST_STRING, return LIST_STRING
         """
+        pattern = unverbosify_regex(pattern)
         assert_re_expression(pattern, allow_empty_groups=True)
 
         match self.stack_last_ret:

{ssc_codegen-0.7.3 → ssc_codegen-0.7.4}/ssc_codegen/document_utlis.py

@@ -1,5 +1,5 @@
 import re
-from typing import TYPE_CHECKING
+from typing import TYPE_CHECKING, Pattern
 
 from ssc_codegen.ast_ssc import (
     BaseExpression,
@@ -16,6 +16,40 @@ if TYPE_CHECKING:
     from .document import BaseDocument
 
 
+# https://stackoverflow.com/a/14919203
+CM1_RX = r"(?m)(?<!\\)((\\{2})*)#.*$"
+CM2_RX = r"(\\)?((\\{2})*)(#)"
+WS_RX = r"(\\)?((\\{2})*)(\s)\s*"
+
+
+def unverbosify_regex(pattern: str | Pattern) -> str:
+    if isinstance(pattern, str):
+        return pattern
+
+    def strip_escapes(match):  # type: ignore
+        ## if even slashes: delete space and retain slashes
+        if match.group(1) is None:
+            return match.group(2)
+        ## if number of slashes is odd: delete slash and keep space (or 'comment')
+        elif match.group(1) == "\\":
+            return match.group(2) + match.group(4)
+        ## error
+        else:
+            raise Exception
+
+    if pattern.flags & re.X:
+        not_verbose_regex = re.sub(
+            WS_RX,
+            strip_escapes,
+            re.sub(
+                CM2_RX, strip_escapes, re.sub(CM1_RX, "\\1", pattern.pattern)
+            ),
+        )
+
+        return not_verbose_regex
+    return pattern.pattern
+
+
 def assert_re_expression(
     pattern: str, allow_empty_groups: bool = False, max_groups: int = -1
 ) -> None: