@tushar-br/desktop 1.0.282 → 1.0.283

package/staging_area/micro projects/SD -Advanced Media Processing Toolkit Automated Downloader, Segmenter & Neural Dubber/.venv/Lib/site-packages/werkzeug/sansio/http.py

@@ -0,0 +1,171 @@
+from __future__ import annotations
+
+import re
+import typing as t
+from datetime import datetime
+
+from .._internal import _dt_as_utc
+from ..http import generate_etag
+from ..http import parse_date
+from ..http import parse_etags
+from ..http import parse_if_range_header
+from ..http import unquote_etag
+
+_etag_re = re.compile(r'([Ww]/)?(?:"(.*?)"|(.*?))(?:\s*,\s*|$)')
+
+
+def is_resource_modified(
+    http_range: str | None = None,
+    http_if_range: str | None = None,
+    http_if_modified_since: str | None = None,
+    http_if_none_match: str | None = None,
+    http_if_match: str | None = None,
+    etag: str | None = None,
+    data: bytes | None = None,
+    last_modified: datetime | str | None = None,
+    ignore_if_range: bool = True,
+) -> bool:
+    """Convenience method for conditional requests.
+    :param http_range: Range HTTP header
+    :param http_if_range: If-Range HTTP header
+    :param http_if_modified_since: If-Modified-Since HTTP header
+    :param http_if_none_match: If-None-Match HTTP header
+    :param http_if_match: If-Match HTTP header
+    :param etag: the etag for the response for comparison.
+    :param data: or alternatively the data of the response to automatically
+                 generate an etag using :func:`generate_etag`.
+    :param last_modified: an optional date of the last modification.
+    :param ignore_if_range: If `False`, `If-Range` header will be taken into
+                            account.
+    :return: `True` if the resource was modified, otherwise `False`.
+
+    .. versionadded:: 2.2
+    """
+    if etag is None and data is not None:
+        etag = generate_etag(data)
+    elif data is not None:
+        raise TypeError("both data and etag given")
+
+    unmodified = False
+    if isinstance(last_modified, str):
+        last_modified = parse_date(last_modified)
+
+    # HTTP doesn't use microsecond, remove it to avoid false positive
+    # comparisons. Mark naive datetimes as UTC.
+    if last_modified is not None:
+        last_modified = _dt_as_utc(last_modified.replace(microsecond=0))
+
+    if_range = None
+    if not ignore_if_range and http_range is not None:
+        # https://tools.ietf.org/html/rfc7233#section-3.2
+        # A server MUST ignore an If-Range header field received in a request
+        # that does not contain a Range header field.
+        if_range = parse_if_range_header(http_if_range)
+
+    if if_range is not None and if_range.date is not None:
+        modified_since: datetime | None = if_range.date
+    else:
+        modified_since = parse_date(http_if_modified_since)
+
+    if modified_since and last_modified and last_modified <= modified_since:
+        unmodified = True
+
+    if etag:
+        etag, _ = unquote_etag(etag)
+        etag = t.cast(str, etag)
+
+        if if_range is not None and if_range.etag is not None:
+            unmodified = parse_etags(if_range.etag).contains(etag)
+        else:
+            if_none_match = parse_etags(http_if_none_match)
+            if if_none_match:
+                # https://tools.ietf.org/html/rfc7232#section-3.2
+                # "A recipient MUST use the weak comparison function when comparing
+                # entity-tags for If-None-Match"
+                unmodified = if_none_match.contains_weak(etag)
+
+            # https://tools.ietf.org/html/rfc7232#section-3.1
+            # "Origin server MUST use the strong comparison function when
+            # comparing entity-tags for If-Match"
+            if_match = parse_etags(http_if_match)
+            if if_match:
+                unmodified = not if_match.is_strong(etag)
+
+    return not unmodified
+
+
+_cookie_re = re.compile(
+    r"""
+    ([^=;]*)
+    (?:\s*=\s*
+      (
+        "(?:[^\\"]|\\.)*"
+      |
+        .*?
+      )
+    )?
+    \s*;\s*
+    """,
+    flags=re.ASCII | re.VERBOSE,
+)
+_cookie_unslash_re = re.compile(rb"\\([0-3][0-7]{2}|.)")
+
+
+def _cookie_unslash_replace(m: t.Match[bytes]) -> bytes:
+    v = m.group(1)
+
+    if len(v) == 1:
+        return v
+
+    return int(v, 8).to_bytes(1, "big")
+
+
+def parse_cookie(
+    cookie: str | None = None,
+    cls: type[ds.MultiDict] | None = None,
+) -> ds.MultiDict[str, str]:
+    """Parse a cookie from a string.
+
+    The same key can be provided multiple times, the values are stored
+    in-order. The default :class:`MultiDict` will have the first value
+    first, and all values can be retrieved with
+    :meth:`MultiDict.getlist`.
+
+    :param cookie: The cookie header as a string.
+    :param cls: A dict-like class to store the parsed cookies in.
+        Defaults to :class:`MultiDict`.
+
+    .. versionchanged:: 3.0
+        Passing bytes, and the ``charset`` and ``errors`` parameters, were removed.
+
+    .. versionadded:: 2.2
+    """
+    if cls is None:
+        cls = ds.MultiDict
+
+    if not cookie:
+        return cls()
+
+    cookie = f"{cookie};"
+    out = []
+
+    for ck, cv in _cookie_re.findall(cookie):
+        ck = ck.strip()
+        cv = cv.strip()
+
+        if not ck:
+            continue
+
+        if len(cv) >= 2 and cv[0] == cv[-1] == '"':
+            # Work with bytes here, since a UTF-8 character could be multiple bytes.
+            cv = _cookie_unslash_re.sub(
+                _cookie_unslash_replace, cv[1:-1].encode()
+            ).decode(errors="replace")
+
+        out.append((ck, cv))
+
+    return cls(out)
+
+
+# circular dependencies
+from .. import datastructures as ds

package/staging_area/micro projects/SD -Advanced Media Processing Toolkit Automated Downloader, Segmenter & Neural Dubber/.venv/Lib/site-packages/werkzeug/sansio/multipart.py

@@ -0,0 +1,321 @@
+from __future__ import annotations
+
+import re
+import typing as t
+from dataclasses import dataclass
+from enum import auto
+from enum import Enum
+
+from ..datastructures import Headers
+from ..exceptions import RequestEntityTooLarge
+from ..http import parse_options_header
+
+
+class Event:
+    pass
+
+
+@dataclass(frozen=True)
+class Preamble(Event):
+    data: bytes
+
+
+@dataclass(frozen=True)
+class Field(Event):
+    name: str
+    headers: Headers
+
+
+@dataclass(frozen=True)
+class File(Event):
+    name: str
+    filename: str
+    headers: Headers
+
+
+@dataclass(frozen=True)
+class Data(Event):
+    data: bytes
+    more_data: bool
+
+
+@dataclass(frozen=True)
+class Epilogue(Event):
+    data: bytes
+
+
+class NeedData(Event):
+    pass
+
+
+NEED_DATA = NeedData()
+
+
+class State(Enum):
+    PREAMBLE = auto()
+    PART = auto()
+    DATA = auto()
+    DATA_START = auto()
+    EPILOGUE = auto()
+    COMPLETE = auto()
+
+
+# Multipart line breaks MUST be CRLF (\r\n) by RFC-7578, except that
+# many implementations break this and either use CR or LF alone.
+LINE_BREAK = b"(?:\r\n|\n|\r)"
+BLANK_LINE_RE = re.compile(b"(?:\r\n\r\n|\r\r|\n\n)", re.MULTILINE)
+LINE_BREAK_RE = re.compile(LINE_BREAK, re.MULTILINE)
+# Header values can be continued via a space or tab after the linebreak, as
+# per RFC2231
+HEADER_CONTINUATION_RE = re.compile(b"%s[ \t]" % LINE_BREAK, re.MULTILINE)
+# This must be long enough to contain any line breaks plus any
+# additional boundary markers (--) such that they will be found in a
+# subsequent search
+SEARCH_EXTRA_LENGTH = 8
+
+
+class MultipartDecoder:
+    """Decodes a multipart message as bytes into Python events.
+
+    The part data is returned as available to allow the caller to save
+    the data from memory to disk, if desired.
+    """
+
+    def __init__(
+        self,
+        boundary: bytes,
+        max_form_memory_size: int | None = None,
+        *,
+        max_parts: int | None = None,
+    ) -> None:
+        self.buffer = bytearray()
+        self.complete = False
+        self.max_form_memory_size = max_form_memory_size
+        self.max_parts = max_parts
+        self.state = State.PREAMBLE
+        self.boundary = boundary
+
+        # Note in the below \h i.e. horizontal whitespace is used
+        # as [^\S\n\r] as \h isn't supported in python.
+
+        # The preamble must end with a boundary where the boundary is
+        # prefixed by a line break, RFC2046. Except that many
+        # implementations including Werkzeug's tests omit the line
+        # break prefix. In addition the first boundary could be the
+        # epilogue boundary (for empty form-data) hence the matching
+        # group to understand if it is an epilogue boundary.
+        self.preamble_re = re.compile(
+            rb"%s?--%s(--[^\S\n\r]*%s?|[^\S\n\r]*%s)"
+            % (LINE_BREAK, re.escape(boundary), LINE_BREAK, LINE_BREAK),
+            re.MULTILINE,
+        )
+        # A boundary must include a line break prefix and suffix, and
+        # may include trailing whitespace. In addition the boundary
+        # could be the epilogue boundary hence the matching group to
+        # understand if it is an epilogue boundary.
+        self.boundary_re = re.compile(
+            rb"%s--%s(--[^\S\n\r]*%s?|[^\S\n\r]*%s)"
+            % (LINE_BREAK, re.escape(boundary), LINE_BREAK, LINE_BREAK),
+            re.MULTILINE,
+        )
+        self._search_position = 0
+        self._parts_decoded = 0
+
+    def last_newline(self, data: bytes) -> int:
+        try:
+            last_nl = data.rindex(b"\n")
+        except ValueError:
+            last_nl = len(data)
+        try:
+            last_cr = data.rindex(b"\r")
+        except ValueError:
+            last_cr = len(data)
+
+        return min(last_nl, last_cr)
+
+    def receive_data(self, data: bytes | None) -> None:
+        if data is None:
+            self.complete = True
+        elif (
+            self.max_form_memory_size is not None
+            and len(self.buffer) + len(data) > self.max_form_memory_size
+        ):
+            raise RequestEntityTooLarge()
+        else:
+            self.buffer.extend(data)
+
+    def next_event(self) -> Event:
+        event: Event = NEED_DATA
+
+        if self.state == State.PREAMBLE:
+            match = self.preamble_re.search(self.buffer, self._search_position)
+            if match is not None:
+                if match.group(1).startswith(b"--"):
+                    self.state = State.EPILOGUE
+                else:
+                    self.state = State.PART
+                data = bytes(self.buffer[: match.start()])
+                del self.buffer[: match.end()]
+                event = Preamble(data=data)
+                self._search_position = 0
+            else:
+                # Update the search start position to be equal to the
+                # current buffer length (already searched) minus a
+                # safe buffer for part of the search target.
+                self._search_position = max(
+                    0, len(self.buffer) - len(self.boundary) - SEARCH_EXTRA_LENGTH
+                )
+
+        elif self.state == State.PART:
+            match = BLANK_LINE_RE.search(self.buffer, self._search_position)
+            if match is not None:
+                headers = self._parse_headers(self.buffer[: match.start()])
+                # The final header ends with a single CRLF, however a
+                # blank line indicates the start of the
+                # body. Therefore the end is after the first CRLF.
+                headers_end = (match.start() + match.end()) // 2
+                del self.buffer[:headers_end]
+
+                if "content-disposition" not in headers:
+                    raise ValueError("Missing Content-Disposition header")
+
+                disposition, extra = parse_options_header(
+                    headers["content-disposition"]
+                )
+                name = t.cast(str, extra.get("name"))
+                filename = extra.get("filename")
+                if filename is not None:
+                    event = File(
+                        filename=filename,
+                        headers=headers,
+                        name=name,
+                    )
+                else:
+                    event = Field(
+                        headers=headers,
+                        name=name,
+                    )
+                self.state = State.DATA_START
+                self._search_position = 0
+                self._parts_decoded += 1
+
+                if self.max_parts is not None and self._parts_decoded > self.max_parts:
+                    raise RequestEntityTooLarge()
+            else:
+                # Update the search start position to be equal to the
+                # current buffer length (already searched) minus a
+                # safe buffer for part of the search target.
+                self._search_position = max(0, len(self.buffer) - SEARCH_EXTRA_LENGTH)
+
+        elif self.state == State.DATA_START:
+            data, del_index, more_data = self._parse_data(self.buffer, start=True)
+            del self.buffer[:del_index]
+            event = Data(data=data, more_data=more_data)
+            if more_data:
+                self.state = State.DATA
+
+        elif self.state == State.DATA:
+            data, del_index, more_data = self._parse_data(self.buffer, start=False)
+            del self.buffer[:del_index]
+            if data or not more_data:
+                event = Data(data=data, more_data=more_data)
+
+        elif self.state == State.EPILOGUE and self.complete:
+            event = Epilogue(data=bytes(self.buffer))
+            del self.buffer[:]
+            self.state = State.COMPLETE
+
+        if self.complete and isinstance(event, NeedData):
+            raise ValueError(f"Invalid form-data cannot parse beyond {self.state}")
+
+        return event
+
+    def _parse_headers(self, data: bytes) -> Headers:
+        headers: list[tuple[str, str]] = []
+        # Merge the continued headers into one line
+        data = HEADER_CONTINUATION_RE.sub(b" ", data)
+        # Now there is one header per line
+        for line in data.splitlines():
+            line = line.strip()
+
+            if line != b"":
+                name, _, value = line.decode().partition(":")
+                headers.append((name.strip(), value.strip()))
+        return Headers(headers)
+
+    def _parse_data(self, data: bytes, *, start: bool) -> tuple[bytes, int, bool]:
+        # Body parts must start with CRLF (or CR or LF)
+        if start:
+            match = LINE_BREAK_RE.match(data)
+            data_start = t.cast(t.Match[bytes], match).end()
+        else:
+            data_start = 0
+
+        boundary = b"--" + self.boundary
+
+        if self.buffer.find(boundary) == -1:
+            # No complete boundary in the buffer, but there may be
+            # a partial boundary at the end. As the boundary
+            # starts with either a nl or cr find the earliest and
+            # return up to that as data.
+            data_end = del_index = self.last_newline(data[data_start:]) + data_start
+            # If amount of data after last newline is far from
+            # possible length of partial boundary, we should
+            # assume that there is no partial boundary in the buffer
+            # and return all pending data.
+            if (len(data) - data_end) > len(b"\n" + boundary):
+                data_end = del_index = len(data)
+            more_data = True
+        else:
+            match = self.boundary_re.search(data)
+            if match is not None:
+                if match.group(1).startswith(b"--"):
+                    self.state = State.EPILOGUE
+                else:
+                    self.state = State.PART
+                data_end = match.start()
+                del_index = match.end()
+            else:
+                data_end = del_index = self.last_newline(data[data_start:]) + data_start
+            more_data = match is None
+
+        return bytes(data[data_start:data_end]), del_index, more_data
+
+
+class MultipartEncoder:
+    def __init__(self, boundary: bytes) -> None:
+        self.boundary = boundary
+        self.state = State.PREAMBLE
+
+    def send_event(self, event: Event) -> bytes:
+        if isinstance(event, Preamble) and self.state == State.PREAMBLE:
+            self.state = State.PART
+            return event.data
+        elif isinstance(event, (Field, File)) and self.state in {
+            State.PREAMBLE,
+            State.PART,
+            State.DATA,
+        }:
+            data = b"\r\n--" + self.boundary + b"\r\n"
+            data += b'Content-Disposition: form-data; name="%s"' % event.name.encode()
+            if isinstance(event, File):
+                data += b'; filename="%s"' % event.filename.encode()
+            data += b"\r\n"
+            for name, value in t.cast(Field, event).headers:
+                if name.lower() != "content-disposition":
+                    data += f"{name}: {value}\r\n".encode()
+            self.state = State.DATA_START
+            return data
+        elif isinstance(event, Data) and self.state == State.DATA_START:
+            self.state = State.DATA
+            if len(event.data) > 0:
+                return b"\r\n" + event.data
+            else:
+                return event.data
+        elif isinstance(event, Data) and self.state == State.DATA:
+            return event.data
+        elif isinstance(event, Epilogue):
+            self.state = State.COMPLETE
+            return b"\r\n--" + self.boundary + b"--\r\n" + event.data
+        else:
+            raise ValueError(f"Cannot generate {event} in state: {self.state}")