Coverage for src/wiktextract/extractor/es/pronunciation.py: 90%

86 statements  

« prev     ^ index     » next       coverage.py v7.9.2, created at 2025-07-04 10:58 +0000

1from wikitextprocessor import HTMLNode, NodeKind, TemplateNode, WikiNode 

2 

3from ...page import clean_node 

4from ...wxr_context import WiktextractContext 

5from ..share import set_sound_file_url_fields 

6from .models import Sound, WordEntry 

7from .tags import translate_raw_tags 

8 

9# translate table row header to sound model field 

10PRON_GRAF_HEADER_MAP = { 

11 "rimas": "rhymes", 

12 "rima": "rhymes", 

13} 

14 

15 

16def process_pron_graf_template( 

17 wxr: WiktextractContext, word_entry: WordEntry, template_node: TemplateNode 

18) -> None: 

19 # https://es.wiktionary.org/wiki/Plantilla:pron-graf 

20 # this template could create sound data without any parameter 

21 # it expands to a two columns table 

22 expanded_node = wxr.wtp.parse( 

23 wxr.wtp.node_to_wikitext(template_node), expand_all=True 

24 ) 

25 table_nodes = list(expanded_node.find_child(NodeKind.TABLE)) 

26 if len(table_nodes) == 0: 26 ↛ 27line 26 didn't jump to line 27 because the condition on line 26 was never true

27 return 

28 table_node = table_nodes[0] 

29 extra_sounds = {} # not translated 

30 for table_row in table_node.find_child(NodeKind.TABLE_ROW): 

31 table_cells = list(table_row.find_child(NodeKind.TABLE_CELL)) 

32 if len(table_cells) != 2: 

33 continue 

34 header_node, value_node = table_cells 

35 header_text = clean_node(wxr, None, header_node) 

36 value_text = clean_node(wxr, None, value_node) 

37 if header_text.endswith(" (AFI)"): # IPA 

38 process_pron_graf_ipa_cell(wxr, word_entry, value_node, header_text) 

39 elif header_text == "silabación": 

40 word_entry.hyphenation = value_text 

41 elif header_text in PRON_GRAF_HEADER_MAP: 

42 sound = Sound() 

43 setattr(sound, PRON_GRAF_HEADER_MAP[header_text], value_text) 

44 word_entry.sounds.append(sound) 

45 elif ( 

46 header_text.endswith(" alternativas") or header_text == "variantes" 

47 ): 

48 process_pron_graf_link_cell( 

49 wxr, word_entry, value_node, header_text, "alternative" 

50 ) 

51 elif header_text == "homófonos": 

52 process_pron_graf_link_cell( 

53 wxr, word_entry, value_node, header_text, "homophone" 

54 ) 

55 elif header_text == "transliteraciones": 

56 process_pron_graf_text_cell(wxr, word_entry, value_node, "roman") 

57 elif header_text == "transcripciones silábicas": 57 ↛ 58line 57 didn't jump to line 58 because the condition on line 57 was never true

58 process_pron_graf_text_cell(wxr, word_entry, value_node, "syllabic") 

59 else: 

60 extra_sounds[header_text] = value_text 

61 

62 if len(extra_sounds) > 0: 

63 word_entry.extra_sounds = extra_sounds 

64 clean_node(wxr, word_entry, expanded_node) 

65 

66 

67def process_pron_graf_ipa_cell( 

68 wxr: WiktextractContext, 

69 word_entry: WordEntry, 

70 cell_node: WikiNode, 

71 header_text: str, 

72) -> None: 

73 sound = Sound() 

74 for node in cell_node.children: 

75 if isinstance(node, str) and len(node.strip()) > 0: 

76 sound.ipa += node.strip() 

77 elif isinstance(node, HTMLNode) and node.tag == "phonos": 

78 sound_file = node.attrs.get("file", "") 

79 set_sound_file_url_fields(wxr, sound_file, sound) 

80 for small_tag in node.find_html("small"): 

81 location = clean_node(wxr, None, small_tag) 

82 sound.raw_tags.append(location) 

83 elif ( 

84 isinstance(node, HTMLNode) and node.tag == "br" and sound != Sound() 

85 ): 

86 if not header_text.startswith("pronunciación"): # location 

87 sound.raw_tags.append(header_text.removesuffix(" (AFI)")) 

88 translate_raw_tags(sound) 

89 word_entry.sounds.append(sound.model_copy(deep=True)) 

90 sound = Sound() 

91 if sound != Sound(): 91 ↛ 92line 91 didn't jump to line 92 because the condition on line 91 was never true

92 if not header_text.startswith("pronunciación"): 

93 sound.raw_tags.append(header_text.removesuffix(" (AFI)")) 

94 translate_raw_tags(sound) 

95 word_entry.sounds.append(sound) 

96 

97 

98def process_pron_graf_link_cell( 

99 wxr: WiktextractContext, 

100 word_entry: WordEntry, 

101 cell_node: WikiNode, 

102 header_text: str, 

103 field_name: str, 

104) -> None: 

105 for link_index, link_node in cell_node.find_child( 

106 NodeKind.LINK, with_index=True 

107 ): 

108 sound = Sound() 

109 setattr(sound, field_name, clean_node(wxr, None, link_node)) 

110 if ( 

111 link_index + 1 < len(cell_node.children) 

112 and isinstance(cell_node.children[link_index + 1], HTMLNode) 

113 and cell_node.children[link_index + 1].tag == "ref" 

114 ): 

115 # nest "ref" tag is note text 

116 sound.note = clean_node( 

117 wxr, None, cell_node.children[link_index + 1].children 

118 ) 

119 if header_text == "variantes": 119 ↛ 120line 119 didn't jump to line 120 because the condition on line 119 was never true

120 sound.not_same_pronunciation = True 

121 word_entry.sounds.append(sound) 

122 

123 

124def process_pron_graf_text_cell( 

125 wxr: WiktextractContext, 

126 word_entry: WordEntry, 

127 cell_node: WikiNode, 

128 field_name: str, 

129) -> None: 

130 sound = Sound() 

131 for node_index, node in enumerate(cell_node.children): 

132 if isinstance(node, str) and len(node.strip()) > 0: 

133 node = node.strip() 

134 if node.startswith(",&nbsp;"): 

135 node = node.removeprefix(",&nbsp;") 

136 word_entry.sounds.append(sound.model_copy(deep=True)) 

137 sound = Sound() 

138 setattr(sound, field_name, node.strip()) 

139 elif isinstance(node, HTMLNode) and node.tag == "ref": 

140 sound.note = clean_node(wxr, None, node.children) 

141 if len(getattr(sound, field_name)) > 0: 141 ↛ exitline 141 didn't return from function 'process_pron_graf_text_cell' because the condition on line 141 was always true

142 word_entry.sounds.append(sound)