1
  2
  3
  4
  5
  6
  7
  8
  9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
"""The image collector for sphinx.environment."""

import os
from glob import glob
from os import path
from typing import Any, Dict, List, Set

from docutils import nodes
from docutils.nodes import Node
from docutils.utils import relative_path

from sphinx import addnodes
from sphinx.application import Sphinx
from sphinx.environment import BuildEnvironment
from sphinx.environment.collectors import EnvironmentCollector
from sphinx.locale import __
from sphinx.util import logging
from sphinx.util.i18n import get_image_filename_for_language, search_image_for_language
from sphinx.util.images import guess_mimetype

logger = logging.getLogger(__name__)


class ImageCollector(EnvironmentCollector):
    """Image files collector for sphinx.environment."""

    def clear_doc(self, app: Sphinx, env: BuildEnvironment, docname: str) -> None:
        env.images.purge_doc(docname)

    def merge_other(self, app: Sphinx, env: BuildEnvironment,
                    docnames: Set[str], other: BuildEnvironment) -> None:
        env.images.merge_other(docnames, other.images)

    def process_doc(self, app: Sphinx, doctree: nodes.document) -> None:
        """Process and rewrite image URIs."""
        docname = app.env.docname

        for node in doctree.findall(nodes.image):
            # Map the mimetype to the corresponding image.  The writer may
            # choose the best image from these candidates.  The special key * is
            # set if there is only single candidate to be used by a writer.
            # The special key ? is set for nonlocal URIs.
            candidates: Dict[str, str] = {}
            node['candidates'] = candidates
            imguri = node['uri']
            if imguri.startswith('data:'):
                candidates['?'] = imguri
                continue
            elif imguri.find('://') != -1:
                candidates['?'] = imguri
                continue

            if imguri.endswith(os.extsep + '*'):
                # Update `node['uri']` to a relative path from srcdir
                # from a relative path from current document.
                rel_imgpath, full_imgpath = app.env.relfn2path(imguri, docname)
                node['uri'] = rel_imgpath

                if app.config.language:
                    # Search language-specific figures at first
                    i18n_imguri = get_image_filename_for_language(imguri, app.env)
                    _, full_i18n_imgpath = app.env.relfn2path(i18n_imguri, docname)
                    self.collect_candidates(app.env, full_i18n_imgpath, candidates, node)

                self.collect_candidates(app.env, full_imgpath, candidates, node)
            else:
                if app.config.language:
                    # substitute imguri by figure_language_filename
                    # (ex. foo.png -> foo.en.png)
                    imguri = search_image_for_language(imguri, app.env)

                # Update `node['uri']` to a relative path from srcdir
                # from a relative path from current document.
                node['uri'], _ = app.env.relfn2path(imguri, docname)
                candidates['*'] = node['uri']

            # map image paths to unique image names (so that they can be put
            # into a single directory)
            for imgpath in candidates.values():
                app.env.dependencies[docname].add(imgpath)
                if not os.access(path.join(app.srcdir, imgpath), os.R_OK):
                    logger.warning(__('image file not readable: %s') % imgpath,
                                   location=node, type='image', subtype='not_readable')
                    continue
                app.env.images.add_file(docname, imgpath)

    def collect_candidates(self, env: BuildEnvironment, imgpath: str,
                           candidates: Dict[str, str], node: Node) -> None:
        globbed: Dict[str, List[str]] = {}
        for filename in glob(imgpath):
            new_imgpath = relative_path(path.join(env.srcdir, 'dummy'),
                                        filename)
            try:
                mimetype = guess_mimetype(filename)
                if mimetype is None:
                    basename, suffix = path.splitext(filename)
                    mimetype = 'image/x-' + suffix[1:]
                if mimetype not in candidates:
                    globbed.setdefault(mimetype, []).append(new_imgpath)
            except OSError as err:
                logger.warning(__('image file %s not readable: %s') % (filename, err),
                               location=node, type='image', subtype='not_readable')
        for key, files in globbed.items():
            candidates[key] = sorted(files, key=len)[0]  # select by similarity


class DownloadFileCollector(EnvironmentCollector):
    """Download files collector for sphinx.environment."""

    def clear_doc(self, app: Sphinx, env: BuildEnvironment, docname: str) -> None:
        env.dlfiles.purge_doc(docname)

    def merge_other(self, app: Sphinx, env: BuildEnvironment,
                    docnames: Set[str], other: BuildEnvironment) -> None:
        env.dlfiles.merge_other(docnames, other.dlfiles)

    def process_doc(self, app: Sphinx, doctree: nodes.document) -> None:
        """Process downloadable file paths. """
        for node in doctree.findall(addnodes.download_reference):
            targetname = node['reftarget']
            if '://' in targetname:
                node['refuri'] = targetname
            else:
                rel_filename, filename = app.env.relfn2path(targetname, app.env.docname)
                app.env.dependencies[app.env.docname].add(rel_filename)
                if not os.access(filename, os.R_OK):
                    logger.warning(__('download file not readable: %s') % filename,
                                   location=node, type='download', subtype='not_readable')
                    continue
                node['filename'] = app.env.dlfiles.add_file(app.env.docname, rel_filename)


def setup(app: Sphinx) -> Dict[str, Any]:
    app.add_env_collector(ImageCollector)
    app.add_env_collector(DownloadFileCollector)

    return {
        'version': 'builtin',
        'parallel_read_safe': True,
        'parallel_write_safe': True,
    }