Мне нужно было преобразовать содержимое Gtk TextBuffer с разметкой расширенного текста Pango в HTML, формат, в котором данные хранятся в приложении, аналогично вашим требованиям.
Я не мог найти простого способа сделать это из коробки, и в итоге я написал свой собственный конвертер из сериализованного содержимого Gtk в html.
Он использует html
, который является частью стандартной библиотеки, и, поскольку у нас уже есть BeautifulSoup4
в качестве зависимости, он также использует его.
Во-первых, мы определили класс, производный от Gtk.TextBuffer
, который перезаписывает метод get_text
, который возвращает содержимое в виде текста или HTML, когда установлено include_hidden_chars
:
class PangoBuffer(Gtk.TextBuffer):
def get_text(self,
start: Optional[Gtk.TextIter] = None,
end: Optional[Gtk.TextIter] = None,
include_hidden_chars: bool = False) -> str:
"""Get the buffer content.
If `include_hidden_chars` is set, then the html markup content is
returned. If False, then the text only is returned."""
if start is None:
start = self.get_start_iter()
if end is None:
end = self.get_end_iter()
if include_hidden_chars is False:
return super().get_text(start, end, include_hidden_chars=False)
else:
format_ = self.register_serialize_tagset()
content = self.serialize(self, format_, start, end)
return PangoToHtml().feed(content)
Важные части находятся в блоке else
. Я бы предпочел разработать собственный сериализатор, но документации мало. Поэтому мы используем встроенный сериализатор, возвращающий двоичное содержимое.
Этот контент в основном представляет собой XML-разметку с дополнительным заголовком и нижним колонтитулом:
# Truncated for legibility.
GTKTEXTBUFFERCONTENTS-0001\x00\x00\x07Z
<text_view_markup>
<tags>
<tag id="12" priority="12"> </tag> # Tags can be empty
<tag name="italic" priority="2">
<attr name="style" type="PangoStyle" value="PANGO_STYLE_ITALIC" />
</tag>
<tag id="7" priority="7">
<attr name="background-gdk" type="GdkColor" value="0:0:ffff" />
<attr name="style" type="PangoStyle" value="PANGO_STYLE_ITALIC" />
<attr name="weight" type="gint" value="700" />
</tag>
</tags>
<text>
<apply_tag name="italic">This is italic</apply_tag>
<apply_tag id="1">. </apply_tag>
<apply_tag id="2">This is italic</apply_tag>
<apply_tag id="3">\n </apply_tag>
<apply_tag id="7">This is bold, italic, and has background colouring.</apply_tag>
</text>
</text_view_markup>
Отсюда мы можем установить, что теги не отсортированы, и они могут иметь либо id
, либо name
.
Теги, содержащие id
, называются анонимными и обычно создаются Pango при десериализации контента.
Именованные теги обычно определяются в вашем приложении:
tag_bold = TextBuffer.create_tag("bold", weight=Pango.Weight.BOLD)
tag_italic = TextBuffer.create_tag("italic", style=Pango.Style.ITALIC)
tag_underline = TextBuffer.create_tag("underline", underline=Pango.Underline.SINGLE)
Заголовок содержит контрольную сумму, которая не может быть десериализована при вызове bytes.decode
, поэтому ее необходимо удалить перед декодированием в строку xml.
Затем класс PangoToHtml
выполняет фактическую работу:
from html.parser import HTMLParser
from typing import Dict, List, Tuple
from bs4 import BeautifulSoup
from bs4.element import Tag
from gi.repository import Pango
class PangoToHtml(HTMLParser):
"""Decode a subset of Pango markup and serialize it as HTML.
Only the Pango markup used within Gourmet is handled, although expanding it
is not difficult.
Due to the way that Pango attributes work, the HTML is not necessarily the
simplest. For example italic tags may be closed early and reopened if other
attributes, eg. bold, are inserted mid-way:
<i> italic text </i><i><u>and underlined</u></i>
This means that the HTML resulting from the conversion by this object may
differ from the original that was fed to the caller.
"""
def __init__(self):
super().__init__()
self.markup_text: str = "" # the resulting content
self.current_opening_tags: str = "" # used during parsing
self.current_closing_tags: List = [] # used during parsing
# The key is the Pango id of a tag, and the value is a tuple of opening
# and closing html tags for this id.
self.tags: Dict[str: Tuple[str, str]] = {}
# Optionally, links can be specified, in a {link text: target} format.
self.links: Dict[str, str] = {}
# If links are specified, it is possible to ignore them, as is done with
# time links.
self.ignore_links: bool = False
# Used as heuristics for parsing links, when applicable.
self.is_colored_and_underlined: bool = False
tag2html: Dict[str, Tuple[str, str]] = {
Pango.Style.ITALIC.value_name: ("<i>", "</i>"), # Pango doesn't do <em>
str(Pango.Weight.BOLD.real): ("<b>", "</b>"),
Pango.Underline.SINGLE.value_name: ("<u>", "</u>"),
"foreground-gdk": (r'<span foreground="{}">', "</span>"),
"background-gdk": (r'<span background="{}">', "</span>")
}
@staticmethod
def pango_to_html_hex(val: str) -> str:
"""Convert 32 bit Pango color hex string to 16 html.
Pango string have the format 'ffff:ffff:ffff' (for white).
These values get truncated to 16 bits per color into a single string:
'#FFFFFF'.
"""
red, green, blue = val.split(":")
red = hex(255 * int(red, base=16) // 65535)[2:].zfill(2)
green = hex(255 * int(green, base=16) // 65535)[2:].zfill(2)
blue = hex(255 * int(blue, base=16) // 65535)[2:].zfill(2)
return f"#{red}{green}{blue}"
def feed(self, data: bytes) -> str:
"""Convert a buffer (text and and the buffer's iterators to html string.
Unlike an HTMLParser, the whole string must be passed at once, chunks
are not supported.
Optionally, a dictionary of links, in the format {text: target}, can be
specified. Links will be inserted if some text in the markup will be
coloured, underlined, and matching an entry in the dictionary.
If `ignore_links` is set, along with the `links` dictionary, then links
will be serialized as regular text, and the link targets will be lost.
"""
# Remove the Pango header: it contains a length mark, which we don't
# care about, but which does not necessarily decodes as valid char.
header_end = data.find(b"<text_view_markup>")
data = data[header_end:].decode()
# Get the tags
tags_begin = data.index("<tags>")
tags_end = data.index("</tags>") + len("</tags>")
tags = data[tags_begin:tags_end]
data = data[tags_end:]
# Get the textual content
text_begin = data.index("<text>")
text_end = data.index("</text>") + len("</text>")
text = data[text_begin:text_end]
# Convert the tags to html.
# We know that only a subset of HTML is handled in Gourmet:
# italics, bold, underlined, normal, and links (coloured & underlined)
soup = BeautifulSoup(tags, features="lxml")
tags = soup.find_all("tag")
tags_list = {}
for tag in tags:
opening_tags = ""
closing_tags = ""
# The tag may have a name, for named tags, or else an id
tag_name = tag.attrs.get('id')
tag_name = tag.attrs.get('name', tag_name)
attributes = [c for c in tag.contents if isinstance(c, Tag)]
for attribute in attributes:
vtype = attribute['type']
value = attribute['value']
name = attribute['name']
if vtype == "GdkColor": # Convert colours to html
if name in ['foreground-gdk', 'background-gdk']:
opening, closing = self.tag2html[name]
hex_color = self.pango_to_html_hex(value)
opening = opening.format(hex_color)
else:
continue # no idea!
else:
opening, closing = self.tag2html[value]
opening_tags += opening
closing_tags = closing + closing_tags # closing tags are FILO
tags_list[tag_name] = opening_tags, closing_tags
if opening_tags:
tags_list[tag_name] = opening_tags, closing_tags
self.tags = tags_list
# Create a single output string that will be sequentially appended to
# during feeding of text. It can then be returned once we've parse all
self.markup_text = ""
self.current_opening_tags = ""
self.current_closing_tags = [] # Closing tags are FILO
self.is_colored_and_underlined = False
super().feed(text)
return self.markup_text
def handle_starttag(self, tag: str, attrs: List[Tuple[str, str]]) -> None:
# The pango tags are either "apply_tag", or "text". We only really care
# about the "apply_tag". There could be an assert, but we let the
# parser quietly handle nonsense.
if tag == "apply_tag":
attrs = dict(attrs)
tag_name = attrs.get('id') # A tag may have a name, or else an id
tag_name = attrs.get('name', tag_name)
tags = self.tags.get(tag_name)
if tags is not None:
self.current_opening_tags, closing_tag = tags
self.current_closing_tags.append(closing_tag)
def handle_data(self, data: str) -> None:
data = self.current_opening_tags + data
self.markup_text += data
def handle_endtag(self, tag: str) -> None:
if self.current_closing_tags: # Can be empty due to closing "text" tag
self.markup_text += self.current_closing_tags.pop()
self.current_opening_tags = ""
Согласно документу HTMLParser, он служит основой для синтаксического анализа текстовых файлов, отформатированных в HTML (язык разметки гипертекста) и XHTML. Мы знаем, что хотим обрабатывать начальные и конечные теги, а также содержимое между ними.
В сериализованном контенте теги упоминаются по их имени или идентификатору, поэтому их необходимо обрабатывать заранее.
В этом случае я решил использовать BeautifulSoup
, так как он предлагает простой способ пройти через теги XML в простом цикле.
Могло ли все это быть сделано только с библиотекой BeautifulSoup
или html
? Наверное да, но мне нужна была поддержка всех видов ссылок, поэтому конечный результат немного отличается, так как мне нужна была гибкость, которую предлагает HTMLParser
.
Вот базовый модульный тест:
from pango_html import PangoToHtml
def test_convert_colors_to_html():
val = "0:0:0"
ret = PangoToHtml.pango_to_html_hex(val)
assert ret == "#000000"
val = "ffff:0:0"
ret = PangoToHtml.pango_to_html_hex(val)
assert ret == "#ff0000"
val = "0:ffff:0"
ret = PangoToHtml.pango_to_html_hex(val)
assert ret == "#00ff00"
val = "0:0:ffff"
ret = PangoToHtml.pango_to_html_hex(val)
assert ret == "#0000ff"
val = "ffff:ffff:ffff"
ret = PangoToHtml.pango_to_html_hex(val)
assert ret == "#ffffff"
val = "0:00000000:ffff" # add some arbitrary amounts of leading zeroes
ret = PangoToHtml.pango_to_html_hex(val)
assert ret == "#0000ff"
val = "ff00:d700:0000"
ret = PangoToHtml.pango_to_html_hex(val)
assert ret == "#fed600" # Gold
val = "ffff:1414:9393"
ret = PangoToHtml.pango_to_html_hex(val)
assert ret == "#ff1493" # Deep Pink
val = "4747:5f5f:9494"
ret = PangoToHtml.pango_to_html_hex(val)
assert ret == "#475f94" # Some Blue
val = "00fd:ffdc:ff5c"
ret = PangoToHtml.pango_to_html_hex(val)
assert ret == "#00fefe" # Some other blue
def test_pango_markup_to_html():
# These are examples found throughout the application
pango_markup = b'GTKTEXTBUFFERCONTENTS-0001\x00\x00\x07Z <text_view_markup>\n <tags>\n <tag id="12" priority="12">\n </tag>\n <tag id="2" priority="2">\n <attr name="style" type="PangoStyle" value="PANGO_STYLE_ITALIC" />\n </tag>\n <tag id="8" priority="8">\n </tag>\n <tag id="3" priority="3">\n </tag>\n <tag id="7" priority="7">\n <attr name="background-gdk" type="GdkColor" value="0:0:ffff" />\n </tag>\n <tag id="4" priority="4">\n <attr name="style" type="PangoStyle" value="PANGO_STYLE_ITALIC" />\n <attr name="weight" type="gint" value="700" />\n </tag>\n <tag id="5" priority="5">\n <attr name="style" type="PangoStyle" value="PANGO_STYLE_ITALIC" />\n <attr name="weight" type="gint" value="700" />\n <attr name="underline" type="PangoUnderline" value="PANGO_UNDERLINE_SINGLE" />\n </tag>\n <tag id="0" priority="0">\n <attr name="weight" type="gint" value="700" />\n </tag>\n <tag id="1" priority="1">\n </tag>\n <tag id="6" priority="6">\n </tag>\n <tag id="9" priority="9">\n <attr name="foreground-gdk" type="GdkColor" value="0:0:ffff" />\n </tag>\n <tag id="11" priority="11">\n <attr name="background-gdk" type="GdkColor" value="0:0:ffff" />\n <attr name="foreground-gdk" type="GdkColor" value="ffff:ffff:ffff" />\n </tag>\n <tag id="10" priority="10">\n </tag>\n </tags>\n<text><apply_tag id="0">This is bold</apply_tag><apply_tag id="1">. </apply_tag><apply_tag id="2">This is italic</apply_tag><apply_tag id="3">\n </apply_tag><apply_tag id="4">This is bold, italic, and </apply_tag><apply_tag id="5">underlined!</apply_tag><apply_tag id="6">\n </apply_tag><apply_tag id="7">This is a test of bg color</apply_tag><apply_tag id="8">\n </apply_tag><apply_tag id="9">This is a test of fg color</apply_tag><apply_tag id="10">\n </apply_tag><apply_tag id="11">This is a test of fg and bg color</apply_tag><apply_tag id="12">\n +</apply_tag></text>\n</text_view_markup>\n' # noqa
expected = '<b>This is bold</b>. <i>This is italic</i>\n <i><b>This is bold, italic, and </b></i><i><b><u>underlined!</u></b></i>\n <span background="#0000ff">This is a test of bg color</span>\n <span foreground="#0000ff">This is a test of fg color</span>\n <span background="#0000ff"><span foreground="#ffffff">This is a test of fg and bg color</span></span>\n +' # noqa
ret = PangoToHtml().feed(pango_markup)
assert ret == expected
pango_markup = b'GTKTEXTBUFFERCONTENTS-0001\x00\x00\x01i <text_view_markup>\n <tags>\n <tag name="italic" priority="1">\n <attr name="style" type="PangoStyle" value="PANGO_STYLE_ITALIC" />\n </tag>\n <tag name="bold" priority="0">\n <attr name="weight" type="gint" value="700" />\n </tag>\n </tags>\n<text>ddf<apply_tag name="bold">fd<apply_tag name="italic">df</apply_tag>fd</apply_tag>dff</text>\n</text_view_markup>\n' # noqa
expected = 'ddf<b>fd<i>df</i>fd</b>dff'
ret = PangoToHtml().feed(pango_markup)
assert ret == expected
person
Cyril D.
schedule
29.07.2020