Source code for sphinx.transforms.post_transforms.images


    Docutils transforms used by Sphinx.

    :copyright: Copyright 2007-2020 by the Sphinx team, see AUTHORS.
    :license: BSD, see LICENSE for details.

import os
import re
from hashlib import sha1
from math import ceil
from typing import Any, Dict, List, Tuple

from docutils import nodes

from sphinx.application import Sphinx
from sphinx.locale import __
from sphinx.transforms import SphinxTransform
from sphinx.util import epoch_to_rfc1123, rfc1123_to_epoch
from sphinx.util import logging, requests
from sphinx.util.images import guess_mimetype, get_image_extension, parse_data_uri
from sphinx.util.osutil import ensuredir, movefile

logger = logging.getLogger(__name__)

CRITICAL_PATH_CHAR_RE = re.compile('[:;<>|*" ]')

class BaseImageConverter(SphinxTransform):
    def apply(self, **kwargs: Any) -> None:
        for node in self.document.traverse(nodes.image):
            if self.match(node):

    def match(self, node: nodes.image) -> bool:
        return True

    def handle(self, node: nodes.image) -> None:

    def imagedir(self) -> str:
        return os.path.join(, 'images')

class ImageDownloader(BaseImageConverter):
    default_priority = 100

    def match(self, node: nodes.image) -> bool:
        if == []:
            return False
            return False
            return '://' in node['uri']

    def handle(self, node: nodes.image) -> None:
            basename = os.path.basename(node['uri'])
            if '?' in basename:
                basename = basename.split('?')[0]
            if basename == '' or len(basename) > MAX_FILENAME_LEN:
                filename, ext = os.path.splitext(node['uri'])
                basename = sha1(filename.encode()).hexdigest() + ext
            basename = re.sub(CRITICAL_PATH_CHAR_RE, "_", basename)

            dirname = node['uri'].replace('://', '/').translate({ord("?"): "/",
                                                                 ord("&"): "/"})
            if len(dirname) > MAX_FILENAME_LEN:
                dirname = sha1(dirname.encode()).hexdigest()
            ensuredir(os.path.join(self.imagedir, dirname))
            path = os.path.join(self.imagedir, dirname, basename)

            headers = {}
            if os.path.exists(path):
                timestamp = ceil(os.stat(path).st_mtime)  # type: float
                headers['If-Modified-Since'] = epoch_to_rfc1123(timestamp)

            r = requests.get(node['uri'], headers=headers)
            if r.status_code >= 400:
                logger.warning(__('Could not fetch remote image: %s [%d]') %
                               (node['uri'], r.status_code))
      [path] = node['uri']

                if r.status_code == 200:
                    with open(path, 'wb') as f:

                last_modified = r.headers.get('last-modified')
                if last_modified:
                    timestamp = rfc1123_to_epoch(last_modified)
                    os.utime(path, (timestamp, timestamp))

                mimetype = guess_mimetype(path, default='*')
                if mimetype != '*' and os.path.splitext(basename)[1] == '':
                    # append a suffix if URI does not contain suffix
                    ext = get_image_extension(mimetype)
                    newpath = os.path.join(self.imagedir, dirname, basename + ext)
                    movefile(path, newpath)
          [newpath] = node['uri']
                    path = newpath
                node['candidates'][mimetype] = path
                node['uri'] = path
      , path)
        except Exception as exc:
            logger.warning(__('Could not fetch remote image: %s [%s]') % (node['uri'], exc))

class DataURIExtractor(BaseImageConverter):
    default_priority = 150

    def match(self, node: nodes.image) -> bool:
        if == []:
            return False
        elif is True:
            return False
            return node['uri'].startswith('data:')

    def handle(self, node: nodes.image) -> None:
        image = parse_data_uri(node['uri'])
        ext = get_image_extension(image.mimetype)
        if ext is None:
            logger.warning(__('Unknown image format: %s...'), node['uri'][:32],

        ensuredir(os.path.join(self.imagedir, 'embeded'))
        digest = sha1(
        path = os.path.join(self.imagedir, 'embeded', digest + ext)[path] = node['uri']

        with open(path, 'wb') as f:

        node['candidates'][image.mimetype] = path
        node['uri'] = path, path)

def get_filename_for(filename: str, mimetype: str) -> str:
    basename = os.path.basename(filename)
    basename = re.sub(CRITICAL_PATH_CHAR_RE, "_", basename)
    return os.path.splitext(basename)[0] + get_image_extension(mimetype)

[docs]class ImageConverter(BaseImageConverter): """A base class for image converters. An image converter is kind of Docutils transform module. It is used to convert image files which does not supported by builder to appropriate format for that builder. For example, :py:class:`LaTeX builder <.LaTeXBuilder>` supports PDF, PNG and JPEG as image formats. However it does not support SVG images. For such case, to use image converters allows to embed these unsupported images into the document. One of image converters; :ref:`sphinx.ext.imgconverter <sphinx.ext.imgconverter>` can convert a SVG image to PNG format using Imagemagick internally. There are three steps to make your custom image converter: 1. Make a subclass of ``ImageConverter`` class 2. Override ``conversion_rules``, ``is_available()`` and ``convert()`` 3. Register your image converter to Sphinx using :py:meth:`.Sphinx.add_post_transform` """ default_priority = 200 #: A conversion rules the image converter supports. #: It is represented as a list of pair of source image format (mimetype) and #: destination one:: #: #: conversion_rules = [ #: ('image/svg+xml', 'image/png'), #: ('image/gif', 'image/png'), #: ('application/pdf', 'image/png'), #: ] conversion_rules = [] # type: List[Tuple[str, str]] def __init__(self, *args: Any, **kwargs: Any) -> None: self.available = None # type: bool # the converter is available or not. # Will be checked at first conversion super().__init__(*args, **kwargs) def match(self, node: nodes.image) -> bool: if self.available is None: self.available = self.is_available() if not self.available: return False elif set(node['candidates']) & set( # builder supports the image; no need to convert return False else: rule = self.get_conversion_rule(node) if rule: return True else: return False def get_conversion_rule(self, node: nodes.image) -> Tuple[str, str]: for candidate in self.guess_mimetypes(node): for supported in rule = (candidate, supported) if rule in self.conversion_rules: return rule return None
[docs] def is_available(self) -> bool: """Return the image converter is available or not.""" raise NotImplementedError()
def guess_mimetypes(self, node: nodes.image) -> List[str]: if '?' in node['candidates']: return [] elif '*' in node['candidates']: return [guess_mimetype(node['uri'])] else: return node['candidates'].keys() def handle(self, node: nodes.image) -> None: _from, _to = self.get_conversion_rule(node) if _from in node['candidates']: srcpath = node['candidates'][_from] else: srcpath = node['candidates']['*'] filename = get_filename_for(srcpath, _to) ensuredir(self.imagedir) destpath = os.path.join(self.imagedir, filename) abs_srcpath = os.path.join(, srcpath) if self.convert(abs_srcpath, destpath): if '*' in node['candidates']: node['candidates']['*'] = destpath else: node['candidates'][_to] = destpath node['uri'] = destpath self.env.original_image_uri[destpath] = srcpath self.env.images.add_file(self.env.docname, destpath)
[docs] def convert(self, _from: str, _to: str) -> bool: """Convert a image file to expected format. *_from* is a path for source image file, and *_to* is a path for destination file. """ raise NotImplementedError()
def setup(app: Sphinx) -> Dict[str, Any]: app.add_post_transform(ImageDownloader) app.add_post_transform(DataURIExtractor) return { 'version': 'builtin', 'parallel_read_safe': True, 'parallel_write_safe': True, }