ssc_codegen 0.25.1__tar.gz → 0.26.0__tar.gz

{ssc_codegen-0.25.1 → ssc_codegen-0.26.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ssc_codegen
-Version: 0.25.1
+Version: 0.26.0
 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-0.25.1 → ssc_codegen-0.26.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "ssc_codegen"
-version = "0.25.1"
+version = "0.26.0"
 description = "Python-dsl code converter to html parser for web scraping "
 readme = "README.md"
 requires-python = ">=3.10"

{ssc_codegen-0.25.1 → ssc_codegen-0.26.0}/ssc_codegen/converters/request_spec.py

@@ -20,7 +20,7 @@ from ssc_codegen.parsers.http import parse_http_request
 # Groups: 1=NAME, 2=PRIM, 3="[]", 4="?", 5=STYLE.
 _PH = re.compile(
     r"\{\{"
-    r"([A-Za-z][A-Za-z0-9_-]*)"
+    r"([a-z][a-z0-9_-]*)"
     r"(?::(str|int|float|bool))?"
     r"(\[\])?"
     r"(\?)?"

{ssc_codegen-0.25.1 → ssc_codegen-0.26.0}/ssc_codegen/core/expressions.py

@@ -167,7 +167,7 @@ _FLOAT_RE = _re.compile(
     r"[+-]?(?:\d(?:[\d_])*\.\d(?:[\d_])*|\d(?:[\d_])*[eE][+-]?\d(?:[\d_])*|\d(?:[\d_]*)\.\d(?:[\d_]*)[eE][+-]?\d(?:[\d_])*)\Z"
 )
 
-_DEFINE_REF_RE = _re.compile(r"\{\{([A-Za-z][A-Za-z0-9_-]*)\}\}")
+_DEFINE_REF_RE = _re.compile(r"\{\{([A-Z_][A-Z0-9_-]*)\}\}")
 
 
 def _resolve_define_references(value: str, ctx: ParseContext) -> str:
@@ -175,7 +175,7 @@ def _resolve_define_references(value: str, ctx: ParseContext) -> str:
         name = m.group(1)
         resolved = ctx.property_defines.get(name)
         if resolved is None:
-            raise ParseError(f"define references undefined name {name!r}")
+            return m.group(0)
         return str(resolved)
 
     return _DEFINE_REF_RE.sub(_replacer, value)

{ssc_codegen-0.25.1 → ssc_codegen-0.26.0}/ssc_codegen/core/linting.py

@@ -1111,12 +1111,24 @@ def lint_rest_cross_refs(ctx: ParseContext, lint: LintContext) -> None:
             )
 
 
+_DEFINE_NAME_RE = _re.compile(r"^[A-Z_][A-Z0-9_-]*\Z")
+
+
 def lint_define_node(
     node: KdlNode, ctx: ParseContext, lint: LintContext
 ) -> None:
     """Validate module-level define."""
     children = lint.get_children_nodes(node)
     args = lint.get_args(node)
+    if args:
+        name = args[0]
+        if not _DEFINE_NAME_RE.match(name):
+            lint.error(
+                node,
+                message=f"define name '{name}' must be UPPER_CASE ([A-Z_][A-Z0-9_-]*)",
+                code="E002",
+                hint="use UPPER_CASE: define MY-VAR=... or define MY_BLOCK { ... }",
+            )
     if children:
         if not args:
             lint.error(

{ssc_codegen-0.25.1 → ssc_codegen-0.26.0}/ssc_codegen/main.py

@@ -264,7 +264,9 @@ def generate(
         out_file = output / kdl_file.with_suffix(ext).name
         logger.debug("processing: %s -> %s", kdl_file, out_file)
         try:
-            ast, err = parse_module(kdl_file.read_text(), source_path=kdl_file)
+            ast, err = parse_module(
+                kdl_file.read_text(encoding="utf-8"), source_path=kdl_file
+            )
             if skip_lint:
                 pass
             else:
@@ -368,7 +370,9 @@ def check(
     total_errors = 0
 
     for kdl_file in kdl_files:
-        _, errs = parse_module(kdl_file.read_text(), source_path=kdl_file)
+        _, errs = parse_module(
+            kdl_file.read_text(encoding="utf-8"), source_path=kdl_file
+        )
         all_results.extend(errs)
 
         if errs:
@@ -488,7 +492,7 @@ def run(
     # Build AST
     try:
         module_ast, errs = parse_module(
-            kdl_path.read_text(), source_path=kdl_path
+            kdl_path.read_text(encoding="utf-8"), source_path=kdl_path
         )
         if errs:
             for e in format_diagnostics(errs, fmt=fmt.value):
@@ -649,7 +653,9 @@ def health(
 
     # Build AST
     try:
-        module_ast, _ = parse_module(kdl_path.read_text(), source_path=kdl_path)
+        module_ast, _ = parse_module(
+            kdl_path.read_text(encoding="utf-8"), source_path=kdl_path
+        )
         if css_to_xpath:
             from ssc_codegen.document_utils import convert_css_to_xpath_module