ssc_codegen 0.26.5__tar.gz → 0.28.0__tar.gz

{ssc_codegen-0.26.5 → ssc_codegen-0.28.0}/.gitignore

@@ -146,5 +146,9 @@ test_schemas/
 .idea/inspectionProfiles/Project_Default.xml
 .idea/libraries/Dart_SDK.xml
 
+# Node.js
+node_modules/
+package-lock.json
+
 # slopmachines
 .claude/*

{ssc_codegen-0.26.5 → ssc_codegen-0.28.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ssc_codegen
-Version: 0.26.5
+Version: 0.28.0
 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
@@ -154,3 +154,14 @@ uv build --wheel         # build wheel
 uv run pytest            # run tests
 uv run ruff check ssc_codegen/
 ```
+
+### Test dependencies
+
+Python tests require only `uv sync`. JS integration tests additionally need:
+
+```bash
+npm install      # installs jsdom (dev dependency in package.json)
+```
+
+Node.js must be installed and available as `node` in PATH. JS tests are automatically skipped if Node.js is not found.
+```

{ssc_codegen-0.26.5 → ssc_codegen-0.28.0}/README.md

@@ -122,3 +122,14 @@ uv build --wheel         # build wheel
 uv run pytest            # run tests
 uv run ruff check ssc_codegen/
 ```
+
+### Test dependencies
+
+Python tests require only `uv sync`. JS integration tests additionally need:
+
+```bash
+npm install      # installs jsdom (dev dependency in package.json)
+```
+
+Node.js must be installed and available as `node` in PATH. JS tests are automatically skipped if Node.js is not found.
+```

{ssc_codegen-0.26.5 → ssc_codegen-0.28.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "ssc_codegen"
-version = "0.26.5"
+version = "0.28.0"
 description = "Python-dsl code converter to html parser for web scraping "
 readme = "README.md"
 requires-python = ">=3.10"
@@ -64,6 +64,7 @@ dev = [
     "mypy>=1.14.1",
     "parsel>=1.9.1",
     "pytest>=8.3.4",
+    "respx>=0.23.1",
     "ruff>=0.9.3",
     "selectolax>=0.3.27",
 ]

{ssc_codegen-0.26.5 → ssc_codegen-0.28.0}/ssc_codegen/ast/__init__.py

@@ -1,179 +1,189 @@
-# mypy: ignore-errors
-"""
-AST nodes for the KDL Schema DSL.
-
-Import everything from here:
-    from kdl_ast import Module, Field, CssSelect, ...
-"""
-from .types import VariableType, StructType
-
-from .base import Node
-
-from .module import (
-    Module,
-    CodeStartHook,
-    CodeEndHook,
-    Docstring,
-    Imports,
-    Utilities,
-)
-
-from .typedef import TypeDef, TypeDefField
-
-from .jsondef import JsonDef, JsonDefField
-
-from .struct import (
-    Struct,
-    StructDocstring,
-    PreValidate,
-    CheckMethod,
-    Init,
-    InitField,
-    SplitDoc,
-    Key,
-    Value,
-    TableConfig,
-    TableRow,
-    TableMatchKey,
-    RequestConfig,
-    ErrorResponse,
-    PlaceholderSpec,
-    Field,
-    StartParse,
-)
-
-from .selectors import (
-    CssSelect,
-    CssSelectAll,
-    XpathSelect,
-    XpathSelectAll,
-    CssRemove,
-    XpathRemove,
-)
-
-from .extract import Text, Raw, Attr
-
-from .string import (
-    Trim,
-    Ltrim,
-    Rtrim,
-    NormalizeSpace,
-    RmPrefix,
-    RmSuffix,
-    RmPrefixSuffix,
-    Fmt,
-    Repl,
-    ReplMap,
-    Lower,
-    Upper,
-    Split,
-    Join,
-    Unescape,
-)
-
-from .regex import Re, ReAll, ReSub
-
-from .array import Index, Slice, Len, Unique
-
-from .cast import ToInt, ToFloat, ToBool, Jsonify, Nested
-
-from .control import Self, Fallback, FallbackStart, FallbackEnd, Return
-
-from .predicate_containers import Filter, Assert, Match
-
-from .predicate_ops import (
-    PredEq,
-    PredNe,
-    PredGt,
-    PredLt,
-    PredGe,
-    PredLe,
-    PredRange,
-    PredStarts,
-    PredEnds,
-    PredContains,
-    PredIn,
-    PredRe,
-    PredReAny,
-    PredReAll,
-    PredCss,
-    PredXpath,
-    PredHasAttr,
-    PredCountEq,
-    PredCountGt,
-    PredCountLt,
-    PredCountNe,
-    PredCountGe,
-    PredCountLe,
-    PredCountRange,
-    PredAttrEnds,
-    PredAttrEq,
-    PredAttrNe,
-    PredAttrRe,
-    PredAttrStarts,
-    PredAttrContains,
-    PredTextContains,
-    PredTextEnds,
-    PredTextRe,
-    PredTextStarts,
-    LogicNot,
-    LogicAnd,
-    LogicOr,
-)
-
-from .transform import TransformDef, TransformTarget, TransformCall
-
-__all__ = [
-    # types
-    "VariableType", "StructType",
-    # base
-    "Node",
-    # module
-    "Module", "CodeStartHook", "CodeEndHook",
-    "Docstring", "Imports", "Utilities",
-    # typedef
-    "TypeDef", "TypeDefField",
-    # jsondef
-    "JsonDef", "JsonDefField",
-    # struct
-    "Struct", "StructDocstring", "PreValidate", "CheckMethod",
-    "Init", "InitField", "SplitDoc",
-    "Key", "Value",
-    "TableConfig", "TableRow", "TableMatchKey",
-    "RequestConfig", "ErrorResponse", "PlaceholderSpec", "Field", "StartParse",
-    # selectors
-    "CssSelect", "CssSelectAll",
-    "XpathSelect", "XpathSelectAll",
-    "CssRemove", "XpathRemove",
-    # extract
-    "Text", "Raw", "Attr",
-    # string
-    "Trim", "Ltrim", "Rtrim", "NormalizeSpace",
-    "RmPrefix", "RmSuffix", "RmPrefixSuffix",
-    "Fmt", "Repl", "ReplMap",
-    "Lower", "Upper", "Split", "Join", "Unescape",
-    # regex
-    "Re", "ReAll", "ReSub",
-    # array
-    "Index", "Slice", "Len", "Unique",
-    # cast
-    "ToInt", "ToFloat", "ToBool", "Jsonify", "Nested",
-    # control
-    "Self", "Fallback", "FallbackStart", "FallbackEnd", "Return",
-    # predicate containers
-    "Filter", "Assert", "Match",
-    # predicate ops
-    "PredEq", "PredNe",
-    "PredGt", "PredLt", "PredGe", "PredLe", "PredRange",
-    "PredStarts", "PredEnds", "PredContains", "PredIn",
-    "PredRe", "PredReAny", "PredReAll",
-    "PredCss", "PredXpath", "PredHasAttr",
-    "PredAttrEq", "PredAttrNe",
-    "PredAttrStarts", "PredAttrEnds", "PredAttrContains", "PredAttrRe",
-    "PredTextStarts", "PredTextEnds", "PredTextContains", "PredTextRe",
-    "PredCountEq", "PredCountGt", "PredCountLt",
-    "PredCountNe", "PredCountGe", "PredCountLe", "PredCountRange",
-    "LogicNot", "LogicAnd", "LogicOr",
-    # transform
-    "TransformDef", "TransformTarget", "TransformCall",
-]
+# mypy: ignore-errors
+"""
+AST nodes for the KDL Schema DSL.
+
+Import everything from here:
+    from kdl_ast import Module, Field, CssSelect, ...
+"""
+from .types import VariableType, StructType
+
+from .base import Node
+
+from .module import (
+    Module,
+    CodeStartHook,
+    CodeEndHook,
+    Docstring,
+    Imports,
+    ImportsRest,
+    Utilities,
+)
+
+from .typedef import TypeDef, TypeDefField
+
+from .jsondef import JsonDef, JsonDefField
+
+from .struct import (
+    StructBase,
+    StructItem,
+    StructList,
+    StructFlatList,
+    StructDict,
+    StructTable,
+    StructRest,
+    Struct,
+    StructDocstring,
+    PreValidate,
+    CheckMethod,
+    Init,
+    InitField,
+    SplitDoc,
+    Key,
+    Value,
+    TableConfig,
+    TableRow,
+    TableMatchKey,
+    RequestConfig,
+    ErrorResponse,
+    PlaceholderSpec,
+    Field,
+    StartParse,
+)
+
+from .selectors import (
+    CssSelect,
+    CssSelectAll,
+    XpathSelect,
+    XpathSelectAll,
+    CssRemove,
+    XpathRemove,
+)
+
+from .extract import Text, Raw, Attr
+
+from .string import (
+    Trim,
+    Ltrim,
+    Rtrim,
+    NormalizeSpace,
+    RmPrefix,
+    RmSuffix,
+    RmPrefixSuffix,
+    Fmt,
+    Repl,
+    ReplMap,
+    Lower,
+    Upper,
+    Split,
+    Join,
+    Unescape,
+)
+
+from .regex import Re, ReAll, ReSub
+
+from .array import Index, Slice, Len, Unique
+
+from .cast import ToInt, ToFloat, ToBool, Jsonify, Nested
+
+from .control import Self, Fallback, FallbackStart, FallbackEnd, Return
+
+from .predicate_containers import Filter, Assert, Match
+
+from .predicate_ops import (
+    PredEq,
+    PredNe,
+    PredGt,
+    PredLt,
+    PredGe,
+    PredLe,
+    PredRange,
+    PredStarts,
+    PredEnds,
+    PredContains,
+    PredIn,
+    PredRe,
+    PredReAny,
+    PredReAll,
+    PredCss,
+    PredXpath,
+    PredHasAttr,
+    PredCountEq,
+    PredCountGt,
+    PredCountLt,
+    PredCountNe,
+    PredCountGe,
+    PredCountLe,
+    PredCountRange,
+    PredAttrEnds,
+    PredAttrEq,
+    PredAttrNe,
+    PredAttrRe,
+    PredAttrStarts,
+    PredAttrContains,
+    PredTextContains,
+    PredTextEnds,
+    PredTextRe,
+    PredTextStarts,
+    LogicNot,
+    LogicAnd,
+    LogicOr,
+)
+
+from .transform import TransformDef, TransformTarget, TransformCall
+
+__all__ = [
+    # types
+    "VariableType", "StructType",
+    # base
+    "Node",
+    # module
+    "Module", "CodeStartHook", "CodeEndHook",
+    "Docstring", "Imports", "ImportsRest", "Utilities",
+    # typedef
+    "TypeDef", "TypeDefField",
+    # jsondef
+    "JsonDef", "JsonDefField",
+    # struct
+    "StructBase", "StructItem", "StructList", "StructFlatList",
+    "StructDict", "StructTable", "StructRest", "Struct",
+    "StructDocstring", "PreValidate", "CheckMethod",
+    "Init", "InitField", "SplitDoc",
+    "Key", "Value",
+    "TableConfig", "TableRow", "TableMatchKey",
+    "RequestConfig", "ErrorResponse", "PlaceholderSpec", "Field", "StartParse",
+    # selectors
+    "CssSelect", "CssSelectAll",
+    "XpathSelect", "XpathSelectAll",
+    "CssRemove", "XpathRemove",
+    # extract
+    "Text", "Raw", "Attr",
+    # string
+    "Trim", "Ltrim", "Rtrim", "NormalizeSpace",
+    "RmPrefix", "RmSuffix", "RmPrefixSuffix",
+    "Fmt", "Repl", "ReplMap",
+    "Lower", "Upper", "Split", "Join", "Unescape",
+    # regex
+    "Re", "ReAll", "ReSub",
+    # array
+    "Index", "Slice", "Len", "Unique",
+    # cast
+    "ToInt", "ToFloat", "ToBool", "Jsonify", "Nested",
+    # control
+    "Self", "Fallback", "FallbackStart", "FallbackEnd", "Return",
+    # predicate containers
+    "Filter", "Assert", "Match",
+    # predicate ops
+    "PredEq", "PredNe",
+    "PredGt", "PredLt", "PredGe", "PredLe", "PredRange",
+    "PredStarts", "PredEnds", "PredContains", "PredIn",
+    "PredRe", "PredReAny", "PredReAll",
+    "PredCss", "PredXpath", "PredHasAttr",
+    "PredAttrEq", "PredAttrNe",
+    "PredAttrStarts", "PredAttrEnds", "PredAttrContains", "PredAttrRe",
+    "PredTextStarts", "PredTextEnds", "PredTextContains", "PredTextRe",
+    "PredCountEq", "PredCountGt", "PredCountLt",
+    "PredCountNe", "PredCountGe", "PredCountLe", "PredCountRange",
+    "LogicNot", "LogicAnd", "LogicOr",
+    # transform
+    "TransformDef", "TransformTarget", "TransformCall",
+]

{ssc_codegen-0.26.5 → ssc_codegen-0.28.0}/ssc_codegen/ast/module.py

@@ -1,92 +1,108 @@
-from __future__ import annotations
-from dataclasses import dataclass, field
-
-from .base import Node
-
-
-@dataclass
-class Module(Node):
-    """
-    Root node.
-    Build order of body:
-      CodeStartHook → Docstring, Imports, Utilities
-      → JsonDef entries → TypeDef entries → Struct entries
-      → CodeEndHook
-    """
-
-    def __post_init__(self):
-        self.body.extend(
-            [
-                Docstring(parent=self),
-                Imports(parent=self),
-                Utilities(parent=self),
-                CodeStartHook(parent=self),
-            ]
-        )
-
-    @property
-    def docstring(self) -> Docstring:
-        return self.body[0]  # type: ignore
-
-    @property
-    def imports(self) -> Imports:
-        return self.body[1]  # type: ignore
-
-    @property
-    def utilities(self) -> Imports:
-        return self.body[2]  # type: ignore
-
-    @property
-    def code_start(self) -> Imports:
-        return self.body[3]  # type: ignore
-
-
-@dataclass
-class CodeStartHook(Node):
-    """
-    User code insertion point before all generated code.
-    Codegen emits body content verbatim at the top of the output file.
-    """
-
-    pass
-
-
-@dataclass
-class CodeEndHook(Node):
-    """
-    User code insertion point after all generated structs.
-    Codegen emits body content verbatim at the bottom of the output file.
-    """
-
-    pass
-
-
-@dataclass
-class Docstring(Node):
-    """Module-level docstring. DSL: doc "text" """
-
-    value: str = ""
-
-
-@dataclass
-class Imports(Node):
-    """
-    Technical node — codegen inserts required import statements into body.
-    Not produced from DSL directly; populated during codegen phase.
-
-    transform_imports: Dict of imports by target language (e.g., {"py": {...}, "js": {...}})
-                       Collected during parsing when TransformCall nodes are created.
-    """
-
-    libs: list[str] = field(default_factory=list)
-    transform_imports: dict[str, set[str]] = field(default_factory=dict)
-
-
-@dataclass
-class Utilities(Node):
-    """
-    Technical node — codegen inserts shared helper functions into body.
-    Not produced from DSL directly; populated during codegen phase.
-    """
-
-    pass
+from __future__ import annotations
+from dataclasses import dataclass, field
+
+from .base import Node
+
+
+@dataclass
+class Module(Node):
+    """
+    Root node.
+    Build order of body:
+      CodeStartHook → Docstring, Imports, ImportsRest, Utilities
+      → JsonDef entries → TypeDef entries → Struct entries
+      → CodeEndHook
+    """
+
+    def __post_init__(self):
+        self.body.extend(
+            [
+                Docstring(parent=self),
+                Imports(parent=self),
+                ImportsRest(parent=self),
+                Utilities(parent=self),
+                CodeStartHook(parent=self),
+            ]
+        )
+
+    @property
+    def docstring(self) -> Docstring:
+        return self.body[0]  # type: ignore
+
+    @property
+    def imports(self) -> Imports:
+        return self.body[1]  # type: ignore
+
+    @property
+    def imports_rest(self) -> ImportsRest:
+        return self.body[2]  # type: ignore
+
+    @property
+    def utilities(self) -> Utilities:
+        return self.body[3]  # type: ignore
+
+    @property
+    def code_start(self) -> CodeStartHook:
+        return self.body[4]  # type: ignore
+
+
+@dataclass
+class CodeStartHook(Node):
+    """
+    User code insertion point before all generated code.
+    Codegen emits body content verbatim at the top of the output file.
+    """
+
+    pass
+
+
+@dataclass
+class CodeEndHook(Node):
+    """
+    User code insertion point after all generated structs.
+    Codegen emits body content verbatim at the bottom of the output file.
+    """
+
+    pass
+
+
+@dataclass
+class Docstring(Node):
+    """Module-level docstring. DSL: doc "text" """
+
+    value: str = ""
+
+
+@dataclass
+class Imports(Node):
+    """
+    Technical node — codegen inserts required import statements into body.
+    Not produced from DSL directly; populated during codegen phase.
+
+    transform_imports: Dict of imports by target language (e.g., {"py": {...}, "js": {...}})
+                       Collected during parsing when TransformCall nodes are created.
+    """
+
+    libs: list[str] = field(default_factory=list)
+    transform_imports: dict[str, set[str]] = field(default_factory=dict)
+
+
+@dataclass
+class ImportsRest(Node):
+    """
+    Technical node — REST-specific import statements.
+    Emitted only when the module contains at least one StructRest.
+    Populated during codegen phase.
+    """
+
+    libs: list[str] = field(default_factory=list)
+
+
+@dataclass
+class Utilities(Node):
+    """
+    Technical node — codegen inserts shared helper functions into body.
+    Not produced from DSL directly; populated during codegen phase.
+    """
+
+    pass