File size: 6,207 Bytes
3a3c77b | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 | # All rights reserved.
#
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions are
# met:
#
# * Redistributions of source code must retain the above copyright notice,
# this list of conditions and the following disclaimer.
# * Redistributions in binary form must reproduce the above copyright notice,
# this list of conditions and the following disclaimer in the documentation
# and/or other materials provided with the distribution.
# * The name of the author may not be used to endorse or promote products
# derived from this software without specific prior written permission.
#
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
# ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
# POSSIBILITY OF SUCH DAMAGE.
# This module contains code used by _writer.py to track links in pages
# being added to the writer until the links can be resolved.
from typing import TYPE_CHECKING, Optional, Union, cast
from .._utils import logger_warning
from . import ArrayObject, DictionaryObject, IndirectObject, PdfObject, TextStringObject, is_null_or_none
if TYPE_CHECKING:
from .._page import PageObject
from .._reader import PdfReader
from .._writer import PdfWriter
class NamedReferenceLink:
"""Named reference link being preserved until we can resolve it correctly."""
def __init__(self, reference: TextStringObject, source_pdf: "PdfReader") -> None:
"""reference: TextStringObject with named reference"""
self._reference = reference
self._source_pdf = source_pdf
def find_referenced_page(self) -> Union[IndirectObject, None]:
destination = self._source_pdf.named_destinations.get(str(self._reference))
return destination.page if destination else None
def patch_reference(self, target_pdf: "PdfWriter", new_page: IndirectObject) -> None:
"""target_pdf: PdfWriter which the new link went into"""
# point named destination in new PDF to the new page
if str(self._reference) not in target_pdf.named_destinations:
target_pdf.add_named_destination(str(self._reference), new_page.page_number)
class DirectReferenceLink:
"""Direct reference link being preserved until we can resolve it correctly."""
def __init__(self, reference: ArrayObject) -> None:
"""reference: an ArrayObject whose first element is the Page indirect object"""
self._reference = reference
def find_referenced_page(self) -> Union[IndirectObject, None]:
if not self._reference:
return None
return cast(IndirectObject, self._reference[0])
def patch_reference(self, target_pdf: "PdfWriter", new_page: IndirectObject) -> None:
"""target_pdf: PdfWriter which the new link went into"""
self._reference[0] = new_page
ReferenceLink = Union[NamedReferenceLink, DirectReferenceLink]
def extract_links(new_page: "PageObject", old_page: "PageObject") -> list[tuple[ReferenceLink, ReferenceLink]]:
"""Extracts links from two pages on the assumption that the two pages are
the same. Produces one list of (new link, old link) tuples.
Non-link annotations are ignored before pairing to avoid dropping valid
links when one page includes additional non-link annotation entries.
"""
new_annotations = new_page.get("/Annots", ArrayObject()).get_object()
old_annotations = old_page.get("/Annots", ArrayObject()).get_object()
if is_null_or_none(new_annotations):
new_annotations = ArrayObject()
if is_null_or_none(old_annotations):
old_annotations = ArrayObject()
if not isinstance(new_annotations, ArrayObject) or not isinstance(old_annotations, ArrayObject):
logger_warning(
"Expected annotation arrays: %(old_annotations)s %(new_annotations)s. Ignoring annotations.",
source=__name__,
old_annotations=old_annotations,
new_annotations=new_annotations,
)
return []
new_links = [
link
for annotation in new_annotations
if (link := _build_link(annotation, new_page)) is not None
]
old_links = [
link
for annotation in old_annotations
if (link := _build_link(annotation, old_page)) is not None
]
if len(new_links) != len(old_links):
logger_warning(
"Annotation sizes differ: %(old_count)d vs. %(new_count)d",
source=__name__,
old_count=len(old_links),
new_count=len(new_links),
)
return list(zip(new_links, old_links))
def _build_link(indirect_object: IndirectObject, page: "PageObject") -> Optional[ReferenceLink]:
src = cast("PdfReader", page.pdf)
link = cast(DictionaryObject, indirect_object.get_object())
if (not isinstance(link, DictionaryObject)) or link.get("/Subtype") != "/Link":
return None
if "/A" in link:
action = cast(DictionaryObject, link["/A"])
if action.get("/S") != "/GoTo":
return None
if "/D" not in action:
return None
return _create_link(action["/D"], src)
if "/Dest" in link:
return _create_link(link["/Dest"], src)
return None # Nothing to do here
def _create_link(reference: PdfObject, source_pdf: "PdfReader") -> Optional[ReferenceLink]:
if isinstance(reference, TextStringObject):
return NamedReferenceLink(reference, source_pdf)
if isinstance(reference, ArrayObject):
return DirectReferenceLink(reference)
return None
|