ssc_codegen 0.8.13__tar.gz → 0.8.14__tar.gz

{ssc_codegen-0.8.13 → ssc_codegen-0.8.14}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ssc_codegen
-Version: 0.8.13
+Version: 0.8.14
 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-0.8.13 → ssc_codegen-0.8.14}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "ssc_codegen"
-version = "0.8.13"
+version = "0.8.14"
 description = "Python-dsl code converter to html parser for web scraping "
 readme = "README.md"
 requires-python = ">=3.10"

{ssc_codegen-0.8.13 → ssc_codegen-0.8.14}/ssc_codegen/__init__.py

@@ -7,7 +7,7 @@ from ssc_codegen.schema import ItemSchema, DictSchema, ListSchema, FlatListSchem
 
 setup_logger()
 
-VERSION = "0.8.13"
+VERSION = "0.8.14"
 
 
 class __MISSING(object):

{ssc_codegen-0.8.13 → ssc_codegen-0.8.14}/ssc_codegen/ast_build/main.py

@@ -77,15 +77,32 @@ def build_ast_module_parser(
     json_structs = extract_json_structs_from_module(py_module)
     # TODO: API for build single json
     ast_jsons = build_ast_json(ast_module, *json_structs)
-    ast_schemas = [
-        build_ast_struct_parser(
-            sc,
-            ast_module,
-            css_to_xpath=css_to_xpath,
-            xpath_to_css=xpath_to_css,
-        )
-        for sc in schemas
-    ]
+    # TODO: implement analyze-only AST function
+    try:
+        ast_schemas = [
+            build_ast_struct_parser(
+                sc,
+                ast_module,
+                css_to_xpath=css_to_xpath,
+                xpath_to_css=xpath_to_css,
+            )
+            for sc in schemas
+        ]
+    except SyntaxError:
+        # get all schemas exceptions and throw to logs:
+        errors = []
+        for sc in schemas:
+            try:
+                build_ast_struct_parser(
+                    sc,
+                    ast_module,
+                    css_to_xpath=css_to_xpath,
+                    xpath_to_css=xpath_to_css,
+                )
+            except SyntaxError as e:
+                errors.append(e)
+        raise SyntaxError(f"{path}: Founded errors: {len(errors)}")
+
     # TODO: API for build single typedef
     ast_typedefs = build_ast_typedef(ast_module, *ast_schemas)
     module_body.extend(ast_jsons)
@@ -173,7 +190,6 @@ def build_ast_struct_parser(
 ) -> StructParser:
     errors_count = run_analyze_schema(schema)
     if errors_count > 0:
-        # todo: exc
         msg = f"{schema.__name__} founded errors: {errors_count}"
         raise SyntaxError(msg)
     docstring = (
@@ -237,8 +253,7 @@ def _fetch_field_nodes(
         )
         # TODO: add ast tests
         # in inheritance schemas, child classes use same fields are used as in the parent class
-        # avoid duplicate ExprReturn node
-        # second case used in ExprDefaultValueWrapper cases
+        # avoid duplicate ExprReturn or ExprDefaultValueWrapper node
         if (
             document.stack[-1].kind != ExprReturn.kind
             and document.stack[-1].kind != TokenType.EXPR_DEFAULT_END
@@ -335,7 +350,7 @@ def _try_fetch_split_doc_node(
         method = StructPartDocMethod(parent=st_ref)
 
         # in inheritance schemas, child classes use same fields are used as in the parent class
-        # second case used in ExprDefaultValueWrapper cases
+        # avoid duplicate ExprReturn or ExprDefaultValueWrapper node
         if (
             split_doc.stack[-1].kind != ExprReturn.kind
             and split_doc.stack[-1].kind != TokenType.EXPR_DEFAULT_END

{ssc_codegen-0.8.13 → ssc_codegen-0.8.14}/ssc_codegen/document_utlis.py

@@ -31,6 +31,8 @@ CM1_RX = r"(?m)(?<!\\)((\\{2})*)#.*$"
 CM2_RX = r"(\\)?((\\{2})*)(#)"
 WS_RX = r"(\\)?((\\{2})*)(\s)\s*"
 
+RE_CAPTURED_GROUPS = re.compile(r"(?<!\()\((?!\?:)[^)]+\)")
+
 
 def is_ignore_case_regex(pattern: str | Pattern) -> bool:
     if isinstance(pattern, str):
@@ -76,10 +78,14 @@ def analyze_re_expression(
     try:
         re_pattern = re.compile(pattern)
         if not allow_empty_groups and re_pattern.groups == 0:
-            msg = f"`{re_pattern.pattern}` pattern groups is empty"
+            msg = f"`{re_pattern.pattern}` pattern groups is empty."
+            msg += "\nTIP: maybe you remember wrap pattern to brackets `()`?"
             return AnalyzeResult.error(msg)
         elif max_groups != -1 and re_pattern.groups > max_groups:
-            msg = f"`{re_pattern.pattern}` too many groups in pattern, expected {max_groups}"
+            captured_groups = RE_CAPTURED_GROUPS.findall(re_pattern.pattern)
+            msg = f"`{re_pattern.pattern}` too many groups in pattern, expected groups count: {max_groups}."
+            msg += f"\nTIP: fix regular expression for extract {max_groups}:"
+            msg += f"\nGroups founded: {captured_groups}"
             return AnalyzeResult.error(msg)
     except re.error as e:
         msg = f"`{pattern}` wrong regex pattern syntax: {e!r}"