Coverage for src/wiktextract/extractor/es/pos.py: 86%

1import re

3from wikitextprocessor.parser import (

4 LEVEL_KIND_FLAGS,

5 LevelNode,

6 NodeKind,

7 TemplateNode,

8 WikiNode,

11from ...page import clean_node

12from ...wxr_context import WiktextractContext

13from .example import process_ejemplo_template

14from .inflection import process_inflect_template

15from .linkage import process_linkage_template

16from .models import AltForm, Form, Sense, WordEntry

17from .section_titles import LINKAGE_TITLES

18from .tags import ALL_TAGS, translate_raw_tags

21def extract_pos_section(

22 wxr: WiktextractContext,

23 word_entry: WordEntry,

24 level_node: LevelNode,

25 section_title: str,

26) -> None:

27 for raw_tag in section_title.split():

28 if raw_tag in ALL_TAGS:

29 tr_tag = ALL_TAGS[raw_tag]

30 if isinstance(tr_tag, str) and tr_tag not in word_entry.tags:

31 word_entry.tags.append(tr_tag)

32 elif isinstance(tr_tag, list): 32 ↛ 33line 32 didn't jump to line 33 because the condition on line 32 was never true

33 for tag in tr_tag:

34 if tag not in word_entry.tags:

35 word_entry.tags.append(tag)

37 has_list = False

38 for node in level_node.children:

39 if isinstance(node, WikiNode) and node.kind == NodeKind.LIST:

40 has_list = True

41 if node.sarg == ";":

42 for list_item in node.find_child(NodeKind.LIST_ITEM):

43 extract_gloss_list_item(wxr, word_entry, list_item, Sense())

44 elif re.fullmatch(r":+;", node.sarg) is not None: # nested gloss

45 parent_sense = Sense()

46 parent_gloss_num = len(node.sarg) - 1

47 for sense in word_entry.senses[::-1]: 47 ↛ 51line 47 didn't jump to line 51 because the loop on line 47 didn't complete

48 if len(sense.glosses) == parent_gloss_num:

49 parent_sense = sense

50 break

51 for list_item in node.find_child(NodeKind.LIST_ITEM):

52 sense = parent_sense.model_copy(deep=True)

53 sense.sense_index = ""

54 extract_gloss_list_item(wxr, word_entry, list_item, sense)

55 elif node.sarg == ":" and len(word_entry.senses) > 0: 55 ↛ 38line 55 didn't jump to line 38 because the condition on line 55 was always true

56 for list_item in node.find_child(NodeKind.LIST_ITEM):

57 extract_gloss_list_item(

58 wxr, word_entry, list_item, word_entry.senses[-1]

59 )

60 elif isinstance(node, TemplateNode):

61 if node.template_name.startswith("inflect."):

62 process_inflect_template(wxr, word_entry, node)

63 elif node.template_name in ["es.sust", "es.adj", "es.v"]:

64 extract_pos_header_template(wxr, word_entry, node)

65 elif node.template_name.removesuffix("s") in LINKAGE_TITLES: 65 ↛ 66line 65 didn't jump to line 66 because the condition on line 65 was never true

66 process_linkage_template(wxr, word_entry, node)

67 elif node.template_name == "ejemplo" and len(word_entry.senses) > 0:

68 process_ejemplo_template(wxr, word_entry.senses[-1], node)

69 elif node.template_name == "uso" and len(word_entry.senses) > 0:

70 process_uso_template(wxr, word_entry.senses[-1], node)

71 elif node.template_name == "ámbito" and len(word_entry.senses) > 0: 71 ↛ 38line 71 didn't jump to line 38 because the condition on line 71 was always true

72 process_ambito_template(wxr, word_entry.senses[-1], node)

74 if not has_list:

75 sense = Sense()

76 gloss = clean_node(

77 wxr, sense, list(level_node.invert_find_child(LEVEL_KIND_FLAGS))

78 )

79 if gloss != "":

80 sense.glosses.append(gloss)

81 word_entry.senses.append(sense)

84def extract_gloss_list_item(

85 wxr: WiktextractContext,

86 word_entry: WordEntry,

87 list_item: WikiNode,

88 sense: Sense,

89) -> None:

90 if list_item.sarg.endswith(";"):

91 raw_tag_text = clean_node(wxr, sense, list_item.children)

92 for index, node in enumerate(list_item.children): 92 ↛ 101line 92 didn't jump to line 101 because the loop on line 92 didn't complete

93 if isinstance(node, str) and sense.sense_index == "": 93 ↛ 92line 93 didn't jump to line 92 because the condition on line 93 was always true

94 m = re.search(r"[\d.a-z]+", node)

95 if m is not None: 95 ↛ 92line 95 didn't jump to line 92 because the condition on line 95 was always true

96 sense.sense_index = m.group(0)

97 raw_tag_text = clean_node(

98 wxr, sense, list_item.children[index + 1 :]

99 )

100 break

101 for raw_tag in raw_tag_text.split(","):

102 raw_tag = raw_tag.strip()

103 if raw_tag != "":

104 sense.raw_tags.append(raw_tag)

105

106 gloss_nodes = []

107 for node in (

108 list_item.definition

109 if list_item.definition is not None

110 else list_item.children

111 ):

112 if isinstance(node, TemplateNode) and node.template_name.startswith(

113 ("f.", "forma ", "plural")

114 ):

115 process_forma_template(wxr, sense, node)

116 gloss_nodes.append(node)

117 elif not (isinstance(node, WikiNode) and node.kind == NodeKind.LIST):

118 gloss_nodes.append(node)

119

120 gloss_text = clean_node(wxr, sense, gloss_nodes)

121 if gloss_text != "": 121 ↛ 127line 121 didn't jump to line 127 because the condition on line 121 was always true

122 sense.glosses.append(gloss_text)

123 translate_raw_tags(sense)

124 if list_item.sarg.endswith(";"):

125 word_entry.senses.append(sense)

126

127 for node in (

128 list_item.definition

129 if list_item.definition is not None

130 else list_item.children

131 ):

132 if isinstance(node, WikiNode) and node.kind == NodeKind.LIST:

133 for child_list_item in node.find_child(NodeKind.LIST_ITEM):

134 child_sense = sense.model_copy(deep=True)

135 child_sense.sense_index = ""

136 extract_gloss_list_item(

137 wxr, word_entry, child_list_item, child_sense

138 )

139

140

141def process_forma_template(

142 wxr: WiktextractContext, sense: Sense, template: TemplateNode

143) -> None:

144 # https://es.wiktionary.org/wiki/Plantilla:forma_verbo

145 form_of = clean_node(wxr, None, template.template_parameters.get(1, ""))

146 if form_of != "": 146 ↛ exitline 146 didn't return from function 'process_forma_template' because the condition on line 146 was always true

147 sense.form_of.append(AltForm(word=form_of))

148 if (

149 "pronominal" in template.template_parameters

150 or "pronom" in template.template_parameters

151 ):

152 sense.form_of.append(AltForm(word=form_of + "se"))

153 if "form-of" not in sense.tags: 153 ↛ exitline 153 didn't return from function 'process_forma_template' because the condition on line 153 was always true

154 sense.tags.append("form-of")

155

156

157def process_uso_template(

158 wxr: WiktextractContext, sense: Sense, t_node: TemplateNode

159) -> None:

160 # https://es.wiktionary.org/wiki/Plantilla:uso

161 from .tags import USO_TAGS

162

163 for arg_name, arg_value in t_node.template_parameters.items():

164 if isinstance(arg_name, int):

165 arg_value = clean_node(wxr, None, arg_value)

166 if arg_value in USO_TAGS: 166 ↛ 173line 166 didn't jump to line 173 because the condition on line 166 was always true

167 tr_tags = USO_TAGS[arg_value]

168 if isinstance(tr_tags, str): 168 ↛ 170line 168 didn't jump to line 170 because the condition on line 168 was always true

169 sense.tags.append(USO_TAGS[arg_value])

170 elif isinstance(tr_tags, list):

171 sense.tags.extend(USO_TAGS[arg_value])

172 else:

173 sense.raw_tags.append(arg_value)

174

175 clean_node(wxr, sense, t_node) # save category links

176

177

178def process_ambito_template(

179 wxr: WiktextractContext, sense: Sense, t_node: TemplateNode

180) -> None:

181 # https://es.wiktionary.org/wiki/Plantilla:ámbito

182 # location data

183 from .tags import AMBITO_TAGS

184

185 for arg_name, arg_value in t_node.template_parameters.items():

186 if isinstance(arg_name, int): 186 ↛ 185line 186 didn't jump to line 185 because the condition on line 186 was always true

187 arg_value = clean_node(wxr, None, arg_value)

188 if arg_value in AMBITO_TAGS: 188 ↛ 185line 188 didn't jump to line 185 because the condition on line 188 was always true

189 tr_tags = AMBITO_TAGS[arg_value]

190 if isinstance(tr_tags, str): 190 ↛ 192line 190 didn't jump to line 192 because the condition on line 190 was always true

191 sense.tags.append(AMBITO_TAGS[arg_value])

192 elif isinstance(tr_tags, list):

193 sense.tags.extend(tr_tags)

194

195 clean_node(wxr, sense, t_node) # save category links

196

197

198def extract_pos_header_template(

199 wxr: WiktextractContext, word_entry: WordEntry, t_node: TemplateNode

200) -> None:

201 # https://es.wiktionary.org/wiki/Plantilla:es.sust

202 expanded_node = wxr.wtp.parse(

203 wxr.wtp.node_to_wikitext(t_node), expand_all=True

204 )

205 raw_tag = ""

206 for node in expanded_node.children:

207 if isinstance(node, str) and node.strip().endswith(":"):

208 raw_tag = clean_node(wxr, None, node).strip(": ¦()")

209 elif isinstance(node, WikiNode) and node.kind == NodeKind.LINK:

210 form = Form(form=clean_node(wxr, None, node))

211 if form.form == "": 211 ↛ 212line 211 didn't jump to line 212 because the condition on line 211 was never true

212 continue

213 if raw_tag != "": 213 ↛ 217line 213 didn't jump to line 217 because the condition on line 213 was always true

214 for r_tag in raw_tag.split():

215 form.raw_tags.append(r_tag)

216 translate_raw_tags(form)

217 word_entry.forms.append(form)

218 elif isinstance(node, WikiNode) and node.kind == NodeKind.ITALIC:

219 r_tag = clean_node(wxr, None, node)

220 if r_tag != "": 220 ↛ 206line 220 didn't jump to line 206 because the condition on line 220 was always true

221 word_entry.raw_tags.append(r_tag)