Don't use pdfrw anymore

pdfrw is a great piece of software, but we don't know PDF enough to debug the
problems we've met. It's safer to use the new cairo API and get back to manual
edition for attachments and bleed boxes.

We only have two regressions for now:
- some internal links are broken,
- PDF producer is not overwritten.

A mail has been sent to cairo's mailing-list about that:
https://lists.cairographics.org/archives/cairo/2018-August/028694.html

Fix #639, #615, fix #596, fix #565.

docs/install.rst

@@ -3,17 +3,16 @@ Installing
 
 WeasyPrint |version| depends on:
 
-* CPython_ ≥ 3.4
+* CPython_ ≥ 3.4.0
 * cairo_ ≥ 1.15.4 [#]_
 * Pango_ ≥ 1.38.0 [#]_
 * CFFI_ ≥ 0.6
 * html5lib_ ≥ 0.999999999
-* cairocffi_ ≥ 0.5
+* cairocffi_ ≥ 0.9.0
 * tinycss2_ ≥ 0.5
 * cssselect2_ ≥ 0.1
 * CairoSVG_ ≥ 1.0.20
 * Pyphen_ ≥ 0.8
-* pdfrw_ ≥ 0.4
 * GDK-PixBuf_ ≥ 2.25.0 [#]_
 
 .. _CPython: http://www.python.org/
@@ -26,7 +25,6 @@ WeasyPrint |version| depends on:
 .. _cssselect2: https://cssselect2.readthedocs.io/
 .. _CairoSVG: http://cairosvg.org/
 .. _Pyphen: http://pyphen.org/
-.. _pdfrw: https://github.com/pmaupin/pdfrw/
 .. _GDK-PixBuf: https://live.gnome.org/GdkPixbuf
 
 
@@ -81,7 +79,8 @@ WeasyPrint! Otherwise, please copy the full error message and
        you get incomplete SVG renderings, please read `#339
        <https://github.com/Kozea/WeasyPrint/issues/339>`_. If you get invalid
        PDF files, please read `#565
-       <https://github.com/Kozea/WeasyPrint/issues/565>`.
+       <https://github.com/Kozea/WeasyPrint/issues/565>`_. Some PDF metadata
+       including PDF information, hyperlinks and bookmarks require 1.15.4.
 
 .. [#] pango ≥ 1.29.3 is required, but 1.38.0 is needed to handle `@font-face`
        CSS rules.

setup.py

@@ -31,14 +31,13 @@
 
 REQUIREMENTS = [
     # XXX: Keep this in sync with docs/install.rst
+    'cffi>=0.6',
     'html5lib>=0.999999999',
+    'cairocffi>=0.9.0',
     'tinycss2>=0.5',
     'cssselect2>=0.1',
-    'cffi>=0.6',
-    'cairocffi>=0.5',
-    'Pyphen>=0.8',
-    'pdfrw>=0.4',
     'CairoSVG>=1.0.20',
+    'Pyphen>=0.8',
     # C dependencies: Gdk-Pixbuf (optional), Pango, cairo.
 ]
 

weasyprint/document.py

@@ -22,18 +22,20 @@
 from .fonts import FontConfiguration
 from .formatting_structure import boxes
 from .formatting_structure.build import build_formatting_structure
+from .html import W3C_DATE_RE
 from .images import get_image_from_uri as original_get_image_from_uri
 from .layout import layout_document
 from .layout.backgrounds import percentage
 from .logger import LOGGER
-from .pdf import write_pdf_metadata
+from .pdf import write_pdf_attachments
 
 if cairo.cairo_version() < 11504:
     warnings.warn(
-        'There are known rendering problems with cairo < 1.15.4. '
-        'WeasyPrint may work with older versions, but please read the note '
-        'about the needed cairo version on the "Install" page of the '
-        'documentation before reporting bugs.')
+        'There are known rendering problems and missing features with '
+        'cairo < 1.15.4. WeasyPrint may work with older versions, but please '
+        'read the note about the needed cairo version on the "Install" page '
+        'of the documentation before reporting bugs. '
+        'http://weasyprint.readthedocs.io/en/latest/install.html')
 
 
 def _get_matrix(box):
@@ -142,6 +144,31 @@ def _gather_links_and_bookmarks(box, bookmarks, links, anchors, matrix):
         _gather_links_and_bookmarks(child, bookmarks, links, anchors, matrix)
 
 
+def _w3c_date_to_iso(string, attr_name):
+    """Tranform W3C date to ISO-8601 format."""
+    if string is None:
+        return None
+    match = W3C_DATE_RE.match(string)
+    if match is None:
+        LOGGER.warning('Invalid %s date: %r', attr_name, string)
+        return None
+    groups = match.groupdict()
+    iso_date = '%04i-%02i-%02iT%02i:%02i:%02i' % (
+        int(groups['year']),
+        int(groups['month'] or 1),
+        int(groups['day'] or 1),
+        int(groups['hour'] or 0),
+        int(groups['minute'] or 0),
+        int(groups['second'] or 0))
+    if groups['hour']:
+        assert groups['minute']
+        assert groups['tz_hour'].startswith(('+', '-'))
+        assert groups['tz_minute']
+        iso_date += '%+03i:%02i' % (
+            int(groups['tz_hour']), int(groups['tz_minute']))
+    return iso_date
+
+
 class Page(object):
     """Represents a single rendered page.
 
@@ -467,6 +494,31 @@ def make_bookmark_tree(self):
                 last_by_depth.append(children)
         return root
 
+    def add_hyperlinks(self, links, context, scale):
+        """Include hyperlinks in current page."""
+        if cairo.cairo_version() < 11504:
+            return
+
+        # TODO: Instead of using rects, we could use the drawing rectangles
+        # defined by cairo when drawing targets. This would give a feeling
+        # similiar to what browsers do with links that span multiple lines.
+        for link in links:
+            link_type, link_target, rectangle = link
+            if link_type == 'external':
+                attributes = "rect=[{} {} {} {}] uri='{}'".format(
+                    *[i * scale for i in rectangle], link_target)
+            elif link_type == 'internal':
+                page, x, y = link_target
+                attributes = (
+                    'rect=[{} {} {} {}] page={} '
+                    'pos=[{} {}]'.format(
+                        *[i * scale for i in rectangle],
+                        page + 1, x * scale, y * scale))
+            elif link_type == 'attachment':
+                # Attachments are handled in write_pdf_metadata
+                continue
+            context.tag_begin(cairo.TAG_LINK, attributes)
+
     def write_pdf(self, target=None, zoom=1, attachments=None):
         """Paint the pages in a PDF file, with meta-data.
 
@@ -497,8 +549,11 @@ def write_pdf(self, target=None, zoom=1, attachments=None):
         # (1, 1) is overridden by .set_size() below.
         surface = cairo.PDFSurface(file_obj, 1, 1)
         context = cairo.Context(surface)
+
         LOGGER.info('Step 6 - Drawing')
-        for page in self.pages:
+
+        paged_links = list(self.resolve_links())
+        for page, links in zip(self.pages, paged_links):
             surface.set_size(
                 math.floor(scale * (
                     page.width + page.bleed['left'] + page.bleed['right'])),
@@ -508,12 +563,68 @@ def write_pdf(self, target=None, zoom=1, attachments=None):
                 context.translate(
                     page.bleed['left'] * scale, page.bleed['top'] * scale)
                 page.paint(context, scale=scale)
+                self.add_hyperlinks(links, context, scale)
                 surface.show_page()
-        surface.finish()
 
         LOGGER.info('Step 7 - Adding PDF metadata')
-        write_pdf_metadata(self, file_obj, scale, self.metadata, attachments,
-                           self.url_fetcher)
+
+        # TODO: overwrite producer when possible in cairo
+        if cairo.cairo_version() >= 11504:
+            # Set document information
+            for attr, key in (
+                    ('title', cairo.PDF_METADATA_TITLE),
+                    ('description', cairo.PDF_METADATA_SUBJECT),
+                    ('generator', cairo.PDF_METADATA_CREATOR)):
+                value = getattr(self.metadata, attr)
+                if value is not None:
+                    surface.set_metadata(key, value)
+            for attr, key in (
+                    ('authors', cairo.PDF_METADATA_AUTHOR),
+                    ('keywords', cairo.PDF_METADATA_KEYWORDS)):
+                value = getattr(self.metadata, attr)
+                if value is not None:
+                    surface.set_metadata(key, ', '.join(value))
+            for attr, key in (
+                    ('created', cairo.PDF_METADATA_CREATE_DATE),
+                    ('modified', cairo.PDF_METADATA_MOD_DATE)):
+                value = getattr(self.metadata, attr)
+                if value is not None:
+                    surface.set_metadata(key, _w3c_date_to_iso(value, attr))
+
+            # Set bookmarks
+            bookmarks = self.make_bookmark_tree()
+            levels = [cairo.PDF_OUTLINE_ROOT] * len(bookmarks)
+            while bookmarks:
+                title, destination, children = bookmarks.pop(0)
+                page, x, y = destination
+                link_attribs = 'page={} pos=[{} {}]'.format(
+                    page + 1, x * scale, y * scale)
+                outline = surface.add_outline(
+                    levels.pop(), title, link_attribs, 0)
+                levels.extend([outline] * len(children))
+                bookmarks = children + bookmarks
+
+        surface.finish()
+
+        # Add extra PDF metadata: attachments, embedded files
+        attachment_links = [
+            [link for link in page_links if link[0] == 'attachment']
+            for page_links in paged_links]
+        # Write extra PDF metadata only when there is a least one from:
+        # - attachments in metadata
+        # - attachments as function parameters
+        # - attachments as PDF links
+        # - bleed boxes
+        condition = (
+            self.metadata.attachments or
+            attachments or
+            any(attachment_links) or
+            any(any(page.bleed.values()) for page in self.pages))
+        if condition:
+            write_pdf_attachments(
+                file_obj, scale, self.url_fetcher,
+                self.metadata.attachments + (attachments or []),
+                attachment_links, self.pages)
 
         if target is None:
             return file_obj.getvalue()