Coverage for /pythoncovmergedfiles/medio/medio/usr/local/lib/python3.11/site-packages/pypdf/generic/_link.py: 25%

1# All rights reserved. 

2# 

3# Redistribution and use in source and binary forms, with or without 

4# modification, are permitted provided that the following conditions are 

5# met: 

6# 

7# * Redistributions of source code must retain the above copyright notice, 

8# this list of conditions and the following disclaimer. 

9# * Redistributions in binary form must reproduce the above copyright notice, 

10# this list of conditions and the following disclaimer in the documentation 

11# and/or other materials provided with the distribution. 

12# * The name of the author may not be used to endorse or promote products 

13# derived from this software without specific prior written permission. 

14# 

15# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" 

16# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 

17# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE 

18# ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE 

19# LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR 

20# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF 

21# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS 

22# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN 

23# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) 

24# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE 

25# POSSIBILITY OF SUCH DAMAGE. 

26 

27 

28# This module contains code used by _writer.py to track links in pages 

29# being added to the writer until the links can be resolved. 

30 

31from typing import TYPE_CHECKING, Optional, Union, cast 

32 

33from .._utils import logger_warning 

34from . import ArrayObject, DictionaryObject, IndirectObject, PdfObject, TextStringObject, is_null_or_none 

35 

36if TYPE_CHECKING: 

37 from .._page import PageObject 

38 from .._reader import PdfReader 

39 from .._writer import PdfWriter 

40 

41 

42class NamedReferenceLink: 

43 """Named reference link being preserved until we can resolve it correctly.""" 

44 

45 def __init__(self, reference: TextStringObject, source_pdf: "PdfReader") -> None: 

46 """reference: TextStringObject with named reference""" 

47 self._reference = reference 

48 self._source_pdf = source_pdf 

49 

50 def find_referenced_page(self) -> Union[IndirectObject, None]: 

51 destination = self._source_pdf.named_destinations.get(str(self._reference)) 

52 return destination.page if destination else None 

53 

54 def patch_reference(self, target_pdf: "PdfWriter", new_page: IndirectObject) -> None: 

55 """target_pdf: PdfWriter which the new link went into""" 

56 # point named destination in new PDF to the new page 

57 if str(self._reference) not in target_pdf.named_destinations: 

58 target_pdf.add_named_destination(str(self._reference), new_page.page_number) 

59 

60 

61class DirectReferenceLink: 

62 """Direct reference link being preserved until we can resolve it correctly.""" 

63 

64 def __init__(self, reference: ArrayObject) -> None: 

65 """reference: an ArrayObject whose first element is the Page indirect object""" 

66 self._reference = reference 

67 

68 def find_referenced_page(self) -> Union[IndirectObject, None]: 

69 if not self._reference: 

70 return None 

71 return cast(IndirectObject, self._reference[0]) 

72 

73 def patch_reference(self, target_pdf: "PdfWriter", new_page: IndirectObject) -> None: 

74 """target_pdf: PdfWriter which the new link went into""" 

75 self._reference[0] = new_page 

76 

77 

78ReferenceLink = Union[NamedReferenceLink, DirectReferenceLink] 

79 

80 

81def extract_links(new_page: "PageObject", old_page: "PageObject") -> list[tuple[ReferenceLink, ReferenceLink]]: 

82 """Extracts links from two pages on the assumption that the two pages are 

83 the same. Produces one list of (new link, old link) tuples. 

84 

85 Non-link annotations are ignored before pairing to avoid dropping valid 

86 links when one page includes additional non-link annotation entries. 

87 """ 

88 new_annotations = new_page.get("/Annots", ArrayObject()).get_object() 

89 old_annotations = old_page.get("/Annots", ArrayObject()).get_object() 

90 if is_null_or_none(new_annotations): 

91 new_annotations = ArrayObject() 

92 if is_null_or_none(old_annotations): 

93 old_annotations = ArrayObject() 

94 if not isinstance(new_annotations, ArrayObject) or not isinstance(old_annotations, ArrayObject): 

95 logger_warning( 

96 "Expected annotation arrays: %(old_annotations)s %(new_annotations)s. Ignoring annotations.", 

97 source=__name__, 

98 old_annotations=old_annotations, 

99 new_annotations=new_annotations, 

100 ) 

101 return [] 

102 new_links = [ 

103 link 

104 for annotation in new_annotations 

105 if (link := _build_link(annotation, new_page)) is not None 

106 ] 

107 old_links = [ 

108 link 

109 for annotation in old_annotations 

110 if (link := _build_link(annotation, old_page)) is not None 

111 ] 

112 

113 if len(new_links) != len(old_links): 

114 logger_warning( 

115 "Annotation sizes differ: %(old_count)d vs. %(new_count)d", 

116 source=__name__, 

117 old_count=len(old_links), 

118 new_count=len(new_links), 

119 ) 

120 

121 return list(zip(new_links, old_links)) 

122 

123 

124def _build_link(indirect_object: IndirectObject, page: "PageObject") -> Optional[ReferenceLink]: 

125 src = cast("PdfReader", page.pdf) 

126 link = cast(DictionaryObject, indirect_object.get_object()) 

127 if (not isinstance(link, DictionaryObject)) or link.get("/Subtype") != "/Link": 

128 return None 

129 

130 if "/A" in link: 

131 action = cast(DictionaryObject, link["/A"]) 

132 if action.get("/S") != "/GoTo": 

133 return None 

134 

135 if "/D" not in action: 

136 return None 

137 return _create_link(action["/D"], src) 

138 

139 if "/Dest" in link: 

140 return _create_link(link["/Dest"], src) 

141 

142 return None # Nothing to do here 

143 

144 

145def _create_link(reference: PdfObject, source_pdf: "PdfReader") -> Optional[ReferenceLink]: 

146 if isinstance(reference, TextStringObject): 

147 return NamedReferenceLink(reference, source_pdf) 

148 if isinstance(reference, ArrayObject): 

149 return DirectReferenceLink(reference) 

150 return None