ssc_codegen 0.8.19__tar.gz → 0.8.21__tar.gz

{ssc_codegen-0.8.19 → ssc_codegen-0.8.21}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ssc_codegen
-Version: 0.8.19
+Version: 0.8.21
 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-0.8.19 → ssc_codegen-0.8.21}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "ssc_codegen"
-version = "0.8.19"
+version = "0.8.21"
 description = "Python-dsl code converter to html parser for web scraping "
 readme = "README.md"
 requires-python = ">=3.10"

{ssc_codegen-0.8.19 → ssc_codegen-0.8.21}/ssc_codegen/__init__.py

@@ -7,7 +7,7 @@ from ssc_codegen.schema import ItemSchema, DictSchema, ListSchema, FlatListSchem
 
 setup_logger()
 
-VERSION = "0.8.19"
+VERSION = "0.8.21"
 
 
 class __MISSING(object):

{ssc_codegen-0.8.19 → ssc_codegen-0.8.21}/ssc_codegen/ast_/__init__.py

@@ -1,5 +1,5 @@
 from .base import BaseAstNode
-from .nodes_array import ExprIndex, ExprToListLength, ExprListStringJoin
+from .nodes_array import ExprIndex, ExprToListLength, ExprListStringJoin, ExprListUnique
 from .nodes_cast import ExprNested, ExprJsonify, ExprToInt, ExprToFloat, ExprToListInt, ExprToListFloat, ExprToBool
 from .nodes_core import (ExprReturn,
                          ExprNoReturn,

{ssc_codegen-0.8.19 → ssc_codegen-0.8.21}/ssc_codegen/ast_/nodes_array.py

@@ -31,3 +31,11 @@ class ExprToListLength(BaseAstNode[T_EMPTY_KWARGS, tuple]):
     kind: ClassVar[TokenType] = TokenType.EXPR_LIST_LEN
     accept_type: VariableType = VariableType.LIST_ANY
     ret_type: VariableType = VariableType.INT
+
+
+@dataclass(kw_only=True)
+class ExprListUnique(BaseAstNode[T_EMPTY_KWARGS, tuple]):
+    # TODO: support LIST_INT, LIST_FLOAT
+    kind: ClassVar[TokenType] = TokenType.EXPR_LIST_UNIQUE
+    accept_type: VariableType = VariableType.LIST_STRING
+    ret_type: VariableType = VariableType.LIST_STRING

{ssc_codegen-0.8.19 → ssc_codegen-0.8.21}/ssc_codegen/converters/go_goquery.py

@@ -1263,3 +1263,5 @@ def pre_list_str_rm_prefix_and_suffix(
 
 # TODO impl ExprHasAttr, ExprListHasAttr
 # TODO: impl Filter Expr
+# TODO: impl ExprListUnique
+

{ssc_codegen-0.8.19 → ssc_codegen-0.8.21}/ssc_codegen/converters/js_pure.py

@@ -101,6 +101,7 @@ from ssc_codegen.ast_ import (
     FilterStrLenLe,
     FilterStrLenGt,
     FilterStrLenGe,
+    ExprListUnique,
 )
 from ssc_codegen.converters.base import BaseCodeConverter
 from ssc_codegen.converters.helpers import (
@@ -721,7 +722,7 @@ def pre_list_str_rm_prefix_and_suffix(
 def pre_has_attr(node: ExprHasAttr) -> str:
     prv, nxt = prev_next_var(node)
     key, msg = node.unpack_args()
-    expr = f"if (!{prv}?.hasAttribute({key!r}) throw new Error({msg!r});"
+    expr = f"if (!{prv}?.hasAttribute({key!r})) throw new Error({msg!r});"
     if is_last_var_no_ret(node):
         return expr
     return expr + f"let {nxt} = {prv};"
@@ -914,3 +915,11 @@ def pre_filter_str_len_ge(node: FilterStrLenGe) -> str:
     if not is_first_node_cond(node) and is_prev_node_atomic_cond(node):
         return f" && {expr}"
     return expr
+
+
+@CONVERTER(ExprListUnique.kind)
+def pre_list_unique(node: ExprListUnique) -> str:
+    prv, nxt = prev_next_var(node)
+    # save order guaranteed
+    # https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/Set#description
+    return f"let {nxt} = [...new Set({prv})]; "

{ssc_codegen-0.8.19 → ssc_codegen-0.8.21}/ssc_codegen/converters/py_base.py

@@ -103,6 +103,7 @@ from ssc_codegen.ast_ import (
     FilterStrLenLe,
     FilterStrLenGt,
     FilterStrLenGe,
+    ExprListUnique,
 )
 from ssc_codegen.converters.base import (
     BaseCodeConverter,
@@ -271,6 +272,7 @@ class BasePyCodeConverter(BaseCodeConverter):
             FilterStrLenLe.kind: pre_filter_str_len_le,
             FilterStrLenGe.kind: pre_filter_str_len_ge,
             FilterStrLenGt.kind: pre_filter_str_len_gt,
+            ExprListUnique.kind: pre_list_unique,
         }
 
         self.post_definitions = {
@@ -1069,3 +1071,12 @@ def pre_filter_str_len_ge(node: FilterStrLenGe) -> str:
     if not is_first_node_cond(node) and is_prev_node_atomic_cond(node):
         return f" and {expr}"
     return expr
+
+
+def pre_list_unique(node: ExprListUnique) -> str:
+    indent = (
+        INDENT_DEFAULT_BODY if have_default_expr(node) else INDENT_METHOD_BODY
+    )
+    prv, nxt = prev_next_var(node)
+    # use `dict.fromkeys()` instead `set()` for guarantees insertion order (py 3.7+) reason
+    return f"{indent}{nxt} = list(dict.fromkeys({prv}))"

{ssc_codegen-0.8.19 → ssc_codegen-0.8.21}/ssc_codegen/document.py

@@ -75,6 +75,7 @@ from ssc_codegen.ast_ import (
     FilterStrLenLe,
     FilterStrLenGt,
     FilterStrLenGe,
+    ExprListUnique,
 )
 from ssc_codegen.document_utlis import (
     analyze_re_expression,
@@ -487,6 +488,14 @@ class ArrayDocument(BaseDocument):
         self._add(ExprFilter(body=expr.stack))
         return self
 
+    def unique(self) -> Self:
+        """Remove duplicates from array-like object
+
+        - accept LIST_STRING, return LIST_STRING
+        """
+        self._add(ExprListUnique())
+        return self
+
 
 class StringDocument(BaseDocument):
     def rm_prefix(self, substr: str) -> Self:

{ssc_codegen-0.8.19 → ssc_codegen-0.8.21}/ssc_codegen/tokens.py

@@ -146,6 +146,7 @@ class TokenType(IntEnum):
     EXPR_LIST_ANY_INDEX = auto()
     EXPR_LIST_JOIN = auto()
     EXPR_LIST_LEN = auto()
+    EXPR_LIST_UNIQUE = auto()
 
     # ASSERT
     IS_EQUAL = auto()