Update 2025-04-13_16:26:34

venv/lib/python3.11/site-packages/idna/__init__.py

@@ -0,0 +1,45 @@
+from .core import (
+    IDNABidiError,
+    IDNAError,
+    InvalidCodepoint,
+    InvalidCodepointContext,
+    alabel,
+    check_bidi,
+    check_hyphen_ok,
+    check_initial_combiner,
+    check_label,
+    check_nfc,
+    decode,
+    encode,
+    ulabel,
+    uts46_remap,
+    valid_contextj,
+    valid_contexto,
+    valid_label_length,
+    valid_string_length,
+)
+from .intranges import intranges_contain
+from .package_data import __version__
+
+__all__ = [
+    "__version__",
+    "IDNABidiError",
+    "IDNAError",
+    "InvalidCodepoint",
+    "InvalidCodepointContext",
+    "alabel",
+    "check_bidi",
+    "check_hyphen_ok",
+    "check_initial_combiner",
+    "check_label",
+    "check_nfc",
+    "decode",
+    "encode",
+    "intranges_contain",
+    "ulabel",
+    "uts46_remap",
+    "valid_contextj",
+    "valid_contexto",
+    "valid_label_length",
+    "valid_string_length",
+]

venv/lib/python3.11/site-packages/idna/codec.py

@@ -0,0 +1,122 @@
+import codecs
+import re
+from typing import Any, Optional, Tuple
+
+from .core import IDNAError, alabel, decode, encode, ulabel
+
+_unicode_dots_re = re.compile("[\u002e\u3002\uff0e\uff61]")
+
+
+class Codec(codecs.Codec):
+    def encode(self, data: str, errors: str = "strict") -> Tuple[bytes, int]:
+        if errors != "strict":
+            raise IDNAError('Unsupported error handling "{}"'.format(errors))
+
+        if not data:
+            return b"", 0
+
+        return encode(data), len(data)
+
+    def decode(self, data: bytes, errors: str = "strict") -> Tuple[str, int]:
+        if errors != "strict":
+            raise IDNAError('Unsupported error handling "{}"'.format(errors))
+
+        if not data:
+            return "", 0
+
+        return decode(data), len(data)
+
+
+class IncrementalEncoder(codecs.BufferedIncrementalEncoder):
+    def _buffer_encode(self, data: str, errors: str, final: bool) -> Tuple[bytes, int]:
+        if errors != "strict":
+            raise IDNAError('Unsupported error handling "{}"'.format(errors))
+
+        if not data:
+            return b"", 0
+
+        labels = _unicode_dots_re.split(data)
+        trailing_dot = b""
+        if labels:
+            if not labels[-1]:
+                trailing_dot = b"."
+                del labels[-1]
+            elif not final:
+                # Keep potentially unfinished label until the next call
+                del labels[-1]
+                if labels:
+                    trailing_dot = b"."
+
+        result = []
+        size = 0
+        for label in labels:
+            result.append(alabel(label))
+            if size:
+                size += 1
+            size += len(label)
+
+        # Join with U+002E
+        result_bytes = b".".join(result) + trailing_dot
+        size += len(trailing_dot)
+        return result_bytes, size
+
+
+class IncrementalDecoder(codecs.BufferedIncrementalDecoder):
+    def _buffer_decode(self, data: Any, errors: str, final: bool) -> Tuple[str, int]:
+        if errors != "strict":
+            raise IDNAError('Unsupported error handling "{}"'.format(errors))
+
+        if not data:
+            return ("", 0)
+
+        if not isinstance(data, str):
+            data = str(data, "ascii")
+
+        labels = _unicode_dots_re.split(data)
+        trailing_dot = ""
+        if labels:
+            if not labels[-1]:
+                trailing_dot = "."
+                del labels[-1]
+            elif not final:
+                # Keep potentially unfinished label until the next call
+                del labels[-1]
+                if labels:
+                    trailing_dot = "."
+
+        result = []
+        size = 0
+        for label in labels:
+            result.append(ulabel(label))
+            if size:
+                size += 1
+            size += len(label)
+
+        result_str = ".".join(result) + trailing_dot
+        size += len(trailing_dot)
+        return (result_str, size)
+
+
+class StreamWriter(Codec, codecs.StreamWriter):
+    pass
+
+
+class StreamReader(Codec, codecs.StreamReader):
+    pass
+
+
+def search_function(name: str) -> Optional[codecs.CodecInfo]:
+    if name != "idna2008":
+        return None
+    return codecs.CodecInfo(
+        name=name,
+        encode=Codec().encode,
+        decode=Codec().decode,
+        incrementalencoder=IncrementalEncoder,
+        incrementaldecoder=IncrementalDecoder,
+        streamwriter=StreamWriter,
+        streamreader=StreamReader,
+    )
+
+
+codecs.register(search_function)

venv/lib/python3.11/site-packages/idna/compat.py

@@ -0,0 +1,15 @@
+from typing import Any, Union
+
+from .core import decode, encode
+
+
+def ToASCII(label: str) -> bytes:
+    return encode(label)
+
+
+def ToUnicode(label: Union[bytes, bytearray]) -> str:
+    return decode(label)
+
+
+def nameprep(s: Any) -> None:
+    raise NotImplementedError("IDNA 2008 does not utilise nameprep protocol")

venv/lib/python3.11/site-packages/idna/core.py

@@ -0,0 +1,437 @@
+import bisect
+import re
+import unicodedata
+from typing import Optional, Union
+
+from . import idnadata
+from .intranges import intranges_contain
+
+_virama_combining_class = 9
+_alabel_prefix = b"xn--"
+_unicode_dots_re = re.compile("[\u002e\u3002\uff0e\uff61]")
+
+
+class IDNAError(UnicodeError):
+    """Base exception for all IDNA-encoding related problems"""
+
+    pass
+
+
+class IDNABidiError(IDNAError):
+    """Exception when bidirectional requirements are not satisfied"""
+
+    pass
+
+
+class InvalidCodepoint(IDNAError):
+    """Exception when a disallowed or unallocated codepoint is used"""
+
+    pass
+
+
+class InvalidCodepointContext(IDNAError):
+    """Exception when the codepoint is not valid in the context it is used"""
+
+    pass
+
+
+def _combining_class(cp: int) -> int:
+    v = unicodedata.combining(chr(cp))
+    if v == 0:
+        if not unicodedata.name(chr(cp)):
+            raise ValueError("Unknown character in unicodedata")
+    return v
+
+
+def _is_script(cp: str, script: str) -> bool:
+    return intranges_contain(ord(cp), idnadata.scripts[script])
+
+
+def _punycode(s: str) -> bytes:
+    return s.encode("punycode")
+
+
+def _unot(s: int) -> str:
+    return "U+{:04X}".format(s)
+
+
+def valid_label_length(label: Union[bytes, str]) -> bool:
+    if len(label) > 63:
+        return False
+    return True
+
+
+def valid_string_length(label: Union[bytes, str], trailing_dot: bool) -> bool:
+    if len(label) > (254 if trailing_dot else 253):
+        return False
+    return True
+
+
+def check_bidi(label: str, check_ltr: bool = False) -> bool:
+    # Bidi rules should only be applied if string contains RTL characters
+    bidi_label = False
+    for idx, cp in enumerate(label, 1):
+        direction = unicodedata.bidirectional(cp)
+        if direction == "":
+            # String likely comes from a newer version of Unicode
+            raise IDNABidiError("Unknown directionality in label {} at position {}".format(repr(label), idx))
+        if direction in ["R", "AL", "AN"]:
+            bidi_label = True
+    if not bidi_label and not check_ltr:
+        return True
+
+    # Bidi rule 1
+    direction = unicodedata.bidirectional(label[0])
+    if direction in ["R", "AL"]:
+        rtl = True
+    elif direction == "L":
+        rtl = False
+    else:
+        raise IDNABidiError("First codepoint in label {} must be directionality L, R or AL".format(repr(label)))
+
+    valid_ending = False
+    number_type: Optional[str] = None
+    for idx, cp in enumerate(label, 1):
+        direction = unicodedata.bidirectional(cp)
+
+        if rtl:
+            # Bidi rule 2
+            if direction not in [
+                "R",
+                "AL",
+                "AN",
+                "EN",
+                "ES",
+                "CS",
+                "ET",
+                "ON",
+                "BN",
+                "NSM",
+            ]:
+                raise IDNABidiError("Invalid direction for codepoint at position {} in a right-to-left label".format(idx))
+            # Bidi rule 3
+            if direction in ["R", "AL", "EN", "AN"]:
+                valid_ending = True
+            elif direction != "NSM":
+                valid_ending = False
+            # Bidi rule 4
+            if direction in ["AN", "EN"]:
+                if not number_type:
+                    number_type = direction
+                else:
+                    if number_type != direction:
+                        raise IDNABidiError("Can not mix numeral types in a right-to-left label")
+        else:
+            # Bidi rule 5
+            if direction not in ["L", "EN", "ES", "CS", "ET", "ON", "BN", "NSM"]:
+                raise IDNABidiError("Invalid direction for codepoint at position {} in a left-to-right label".format(idx))
+            # Bidi rule 6
+            if direction in ["L", "EN"]:
+                valid_ending = True
+            elif direction != "NSM":
+                valid_ending = False
+
+    if not valid_ending:
+        raise IDNABidiError("Label ends with illegal codepoint directionality")
+
+    return True
+
+
+def check_initial_combiner(label: str) -> bool:
+    if unicodedata.category(label[0])[0] == "M":
+        raise IDNAError("Label begins with an illegal combining character")
+    return True
+
+
+def check_hyphen_ok(label: str) -> bool:
+    if label[2:4] == "--":
+        raise IDNAError("Label has disallowed hyphens in 3rd and 4th position")
+    if label[0] == "-" or label[-1] == "-":
+        raise IDNAError("Label must not start or end with a hyphen")
+    return True
+
+
+def check_nfc(label: str) -> None:
+    if unicodedata.normalize("NFC", label) != label:
+        raise IDNAError("Label must be in Normalization Form C")
+
+
+def valid_contextj(label: str, pos: int) -> bool:
+    cp_value = ord(label[pos])
+
+    if cp_value == 0x200C:
+        if pos > 0:
+            if _combining_class(ord(label[pos - 1])) == _virama_combining_class:
+                return True
+
+        ok = False
+        for i in range(pos - 1, -1, -1):
+            joining_type = idnadata.joining_types.get(ord(label[i]))
+            if joining_type == ord("T"):
+                continue
+            elif joining_type in [ord("L"), ord("D")]:
+                ok = True
+                break
+            else:
+                break
+
+        if not ok:
+            return False
+
+        ok = False
+        for i in range(pos + 1, len(label)):
+            joining_type = idnadata.joining_types.get(ord(label[i]))
+            if joining_type == ord("T"):
+                continue
+            elif joining_type in [ord("R"), ord("D")]:
+                ok = True
+                break
+            else:
+                break
+        return ok
+
+    if cp_value == 0x200D:
+        if pos > 0:
+            if _combining_class(ord(label[pos - 1])) == _virama_combining_class:
+                return True
+        return False
+
+    else:
+        return False
+
+
+def valid_contexto(label: str, pos: int, exception: bool = False) -> bool:
+    cp_value = ord(label[pos])
+
+    if cp_value == 0x00B7:
+        if 0 < pos < len(label) - 1:
+            if ord(label[pos - 1]) == 0x006C and ord(label[pos + 1]) == 0x006C:
+                return True
+        return False
+
+    elif cp_value == 0x0375:
+        if pos < len(label) - 1 and len(label) > 1:
+            return _is_script(label[pos + 1], "Greek")
+        return False
+
+    elif cp_value == 0x05F3 or cp_value == 0x05F4:
+        if pos > 0:
+            return _is_script(label[pos - 1], "Hebrew")
+        return False
+
+    elif cp_value == 0x30FB:
+        for cp in label:
+            if cp == "\u30fb":
+                continue
+            if _is_script(cp, "Hiragana") or _is_script(cp, "Katakana") or _is_script(cp, "Han"):
+                return True
+        return False
+
+    elif 0x660 <= cp_value <= 0x669:
+        for cp in label:
+            if 0x6F0 <= ord(cp) <= 0x06F9:
+                return False
+        return True
+
+    elif 0x6F0 <= cp_value <= 0x6F9:
+        for cp in label:
+            if 0x660 <= ord(cp) <= 0x0669:
+                return False
+        return True
+
+    return False
+
+
+def check_label(label: Union[str, bytes, bytearray]) -> None:
+    if isinstance(label, (bytes, bytearray)):
+        label = label.decode("utf-8")
+    if len(label) == 0:
+        raise IDNAError("Empty Label")
+
+    check_nfc(label)
+    check_hyphen_ok(label)
+    check_initial_combiner(label)
+
+    for pos, cp in enumerate(label):
+        cp_value = ord(cp)
+        if intranges_contain(cp_value, idnadata.codepoint_classes["PVALID"]):
+            continue
+        elif intranges_contain(cp_value, idnadata.codepoint_classes["CONTEXTJ"]):
+            try:
+                if not valid_contextj(label, pos):
+                    raise InvalidCodepointContext(
+                        "Joiner {} not allowed at position {} in {}".format(_unot(cp_value), pos + 1, repr(label))
+                    )
+            except ValueError:
+                raise IDNAError(
+                    "Unknown codepoint adjacent to joiner {} at position {} in {}".format(
+                        _unot(cp_value), pos + 1, repr(label)
+                    )
+                )
+        elif intranges_contain(cp_value, idnadata.codepoint_classes["CONTEXTO"]):
+            if not valid_contexto(label, pos):
+                raise InvalidCodepointContext(
+                    "Codepoint {} not allowed at position {} in {}".format(_unot(cp_value), pos + 1, repr(label))
+                )
+        else:
+            raise InvalidCodepoint(
+                "Codepoint {} at position {} of {} not allowed".format(_unot(cp_value), pos + 1, repr(label))
+            )
+
+    check_bidi(label)
+
+
+def alabel(label: str) -> bytes:
+    try:
+        label_bytes = label.encode("ascii")
+        ulabel(label_bytes)
+        if not valid_label_length(label_bytes):
+            raise IDNAError("Label too long")
+        return label_bytes
+    except UnicodeEncodeError:
+        pass
+
+    check_label(label)
+    label_bytes = _alabel_prefix + _punycode(label)
+
+    if not valid_label_length(label_bytes):
+        raise IDNAError("Label too long")
+
+    return label_bytes
+
+
+def ulabel(label: Union[str, bytes, bytearray]) -> str:
+    if not isinstance(label, (bytes, bytearray)):
+        try:
+            label_bytes = label.encode("ascii")
+        except UnicodeEncodeError:
+            check_label(label)
+            return label
+    else:
+        label_bytes = label
+
+    label_bytes = label_bytes.lower()
+    if label_bytes.startswith(_alabel_prefix):
+        label_bytes = label_bytes[len(_alabel_prefix) :]
+        if not label_bytes:
+            raise IDNAError("Malformed A-label, no Punycode eligible content found")
+        if label_bytes.decode("ascii")[-1] == "-":
+            raise IDNAError("A-label must not end with a hyphen")
+    else:
+        check_label(label_bytes)
+        return label_bytes.decode("ascii")
+
+    try:
+        label = label_bytes.decode("punycode")
+    except UnicodeError:
+        raise IDNAError("Invalid A-label")
+    check_label(label)
+    return label
+
+
+def uts46_remap(domain: str, std3_rules: bool = True, transitional: bool = False) -> str:
+    """Re-map the characters in the string according to UTS46 processing."""
+    from .uts46data import uts46data
+
+    output = ""
+
+    for pos, char in enumerate(domain):
+        code_point = ord(char)
+        try:
+            uts46row = uts46data[code_point if code_point < 256 else bisect.bisect_left(uts46data, (code_point, "Z")) - 1]
+            status = uts46row[1]
+            replacement: Optional[str] = None
+            if len(uts46row) == 3:
+                replacement = uts46row[2]
+            if (
+                status == "V"
+                or (status == "D" and not transitional)
+                or (status == "3" and not std3_rules and replacement is None)
+            ):
+                output += char
+            elif replacement is not None and (
+                status == "M" or (status == "3" and not std3_rules) or (status == "D" and transitional)
+            ):
+                output += replacement
+            elif status != "I":
+                raise IndexError()
+        except IndexError:
+            raise InvalidCodepoint(
+                "Codepoint {} not allowed at position {} in {}".format(_unot(code_point), pos + 1, repr(domain))
+            )
+
+    return unicodedata.normalize("NFC", output)
+
+
+def encode(
+    s: Union[str, bytes, bytearray],
+    strict: bool = False,
+    uts46: bool = False,
+    std3_rules: bool = False,
+    transitional: bool = False,
+) -> bytes:
+    if not isinstance(s, str):
+        try:
+            s = str(s, "ascii")
+        except UnicodeDecodeError:
+            raise IDNAError("should pass a unicode string to the function rather than a byte string.")
+    if uts46:
+        s = uts46_remap(s, std3_rules, transitional)
+    trailing_dot = False
+    result = []
+    if strict:
+        labels = s.split(".")
+    else:
+        labels = _unicode_dots_re.split(s)
+    if not labels or labels == [""]:
+        raise IDNAError("Empty domain")
+    if labels[-1] == "":
+        del labels[-1]
+        trailing_dot = True
+    for label in labels:
+        s = alabel(label)
+        if s:
+            result.append(s)
+        else:
+            raise IDNAError("Empty label")
+    if trailing_dot:
+        result.append(b"")
+    s = b".".join(result)
+    if not valid_string_length(s, trailing_dot):
+        raise IDNAError("Domain too long")
+    return s
+
+
+def decode(
+    s: Union[str, bytes, bytearray],
+    strict: bool = False,
+    uts46: bool = False,
+    std3_rules: bool = False,
+) -> str:
+    try:
+        if not isinstance(s, str):
+            s = str(s, "ascii")
+    except UnicodeDecodeError:
+        raise IDNAError("Invalid ASCII in A-label")
+    if uts46:
+        s = uts46_remap(s, std3_rules, False)
+    trailing_dot = False
+    result = []
+    if not strict:
+        labels = _unicode_dots_re.split(s)
+    else:
+        labels = s.split(".")
+    if not labels or labels == [""]:
+        raise IDNAError("Empty domain")
+    if not labels[-1]:
+        del labels[-1]
+        trailing_dot = True
+    for label in labels:
+        s = ulabel(label)
+        if s:
+            result.append(s)
+        else:
+            raise IDNAError("Empty label")
+    if trailing_dot:
+        result.append("")
+    return ".".join(result)

venv/lib/python3.11/site-packages/idna/intranges.py

@@ -0,0 +1,57 @@
+"""
+Given a list of integers, made up of (hopefully) a small number of long runs
+of consecutive integers, compute a representation of the form
+((start1, end1), (start2, end2) ...). Then answer the question "was x present
+in the original list?" in time O(log(# runs)).
+"""
+
+import bisect
+from typing import List, Tuple
+
+
+def intranges_from_list(list_: List[int]) -> Tuple[int, ...]:
+    """Represent a list of integers as a sequence of ranges:
+    ((start_0, end_0), (start_1, end_1), ...), such that the original
+    integers are exactly those x such that start_i <= x < end_i for some i.
+
+    Ranges are encoded as single integers (start << 32 | end), not as tuples.
+    """
+
+    sorted_list = sorted(list_)
+    ranges = []
+    last_write = -1
+    for i in range(len(sorted_list)):
+        if i + 1 < len(sorted_list):
+            if sorted_list[i] == sorted_list[i + 1] - 1:
+                continue
+        current_range = sorted_list[last_write + 1 : i + 1]
+        ranges.append(_encode_range(current_range[0], current_range[-1] + 1))
+        last_write = i
+
+    return tuple(ranges)
+
+
+def _encode_range(start: int, end: int) -> int:
+    return (start << 32) | end
+
+
+def _decode_range(r: int) -> Tuple[int, int]:
+    return (r >> 32), (r & ((1 << 32) - 1))
+
+
+def intranges_contain(int_: int, ranges: Tuple[int, ...]) -> bool:
+    """Determine if `int_` falls into one of the ranges in `ranges`."""
+    tuple_ = _encode_range(int_, 0)
+    pos = bisect.bisect_left(ranges, tuple_)
+    # we could be immediately ahead of a tuple (start, end)
+    # with start < int_ <= end
+    if pos > 0:
+        left, right = _decode_range(ranges[pos - 1])
+        if left <= int_ < right:
+            return True
+    # or we could be immediately behind a tuple (int_, end)
+    if pos < len(ranges):
+        left, _ = _decode_range(ranges[pos])
+        if left == int_:
+            return True
+    return False

venv/lib/python3.11/site-packages/idna/package_data.py

@@ -0,0 +1 @@
+__version__ = "3.10"