Coverage for src/wiktextract/extractor/pl/pos.py: 78%

1import re

3from wikitextprocessor import LevelNode, NodeKind, TemplateNode, WikiNode

5from ...page import clean_node

6from ...wxr_context import WiktextractContext

7from .models import AltForm, Sense, WordEntry

8from .tags import TAGS, translate_raw_tags

10# All POS categories

11# https://pl.wiktionary.org/wiki/Kategoria:Części_mowy_wg_języków

12# Polish POS

13# https://pl.wiktionary.org/wiki/Kategoria:Części_mowy_języka_polskiego

14POS_DATA = {

15 "czasownik": {"pos": "verb"},

16 "czasownika": {"pos": "verb"},

17 # Szablon:szwedzki czasownik frazowy

18 "czasownik frazowy (partikelverb)": {"pos": "verb", "tags": ["phrase"]},

19 "fraza": {"pos": "phrase"},

20 "klasyfikator": {"pos": "classifier"},

21 "liczebnik": {"pos": "num"},

22 "liczebnikowa": {"pos": "num"},

23 "międzyrostek": {"pos": "interfix", "tags": ["morpheme"]},

24 "morfem": {"pos": "unknown", "tags": ["morpheme"]},

25 "określnik": {"pos": "det"},

26 "partykuła": {"pos": "particle"},

27 "partykułowa": {"pos": "particle"},

28 # Szablon:phrasal verb

29 "phrasal verb (czasownik frazowy)": {"pos": "verb", "tags": ["phrase"]},

30 "przedimek": {"pos": "article"},

31 "przedrostek": {"pos": "prefix", "tags": ["morpheme"]},

32 "przedrostkowy": {"pos": "prefix", "tags": ["morpheme"]},

33 "przyimek": {"pos": "prep"},

34 "przyimkowa": {"pos": "prep_phrase"},

35 "przymiotnik": {"pos": "adj"},

36 "przymiotnikowym": {"pos": "adj"},

37 "przymiotnikowa": {"pos": "adj_phrase"},

38 "przyrostek": {"pos": "suffix", "tags": ["morpheme"]},

39 "przyrostkowy": {"pos": "suffix", "tags": ["morpheme"]},

40 "przysłówek": {"pos": "adv"},

41 "przysłówkowa": {"pos": "adv_phrase"},

42 "pytajny": {"pos": "pron", "tags": ["interrogative"]}, # "zaimek pytajny"

43 "rodzajnik": {"pos": "article", "tags": ["gendered"]},

44 "rzeczownik": {"pos": "noun"},

45 "rzeczownikowa": {"pos": "noun"},

46 "skrótowiec": {"pos": "abbrev", "tags": ["abbreviation"]},

47 "skrót": {"pos": "abbrev", "tags": ["abbreviation"]},

48 "spójnik": {"pos": "conj"},

49 "symbol": {"pos": "symbol"},

50 "wrostek": {"pos": "infix", "tags": ["morpheme"]},

51 "wykrzyknik": {"pos": "intj"},

52 "wykrzyknika": {"pos": "intj"},

53 "wykrzyknikowa": {"pos": "intj"},

54 "zaimka": {"pos": "pron"},

55 "zaimek": {"pos": "pron"},

56 "zaimkowy": {"pos": "pron"},

57 "znak interpunkcyjny": {"pos": "punct", "tags": ["punctuation"]},

58 "dopełniacz saksoński": {"pos": "unknown"},

59 "forma ściągnięta": {

60 "pos": "contraction",

61 "tags": ["contraction", "form-of"],

62 },

63 "słowotwórczy": {"pos": "unknown", "tags": ["morpheme"]},

64 "liczebnik porządkowy": {"pos": "adj", "tags": ["ordinal"]},

65 "liczebnik główny": {"pos": "adj", "tags": ["cardinal"]},

66 "litera": {"pos": "character", "tags": ["letter"]},

67 "związek frazeologiczny": {"pos": "phrase", "tags": ["idiomatic"]},

68 "związek wyrazów": {"pos": "unknown"},

69 "sentencja łacińska": {"pos": "unknown"},

70 "imiesłów": {"pos": "verb", "tags": ["participle"]},

71 "postpozycja": {"pos": "postp"},

72 "zwrot": {"pos": "phrase"},

73 "słowo pomocnicze": {"pos": "unknown"},

74 "wyrażenie": {"pos": "phrase"},

75 "czasownik frazowy": {"pos": "verb", "tags": ["phrasal"]},

76 "zaimek osobowy": {"pos": "pron", "tags": ["person"]},

77 "zaimek pytajny": {"pos": "pron", "tags": ["interrogative"]},

78 "zbitka": {"pos": "unknown"},

79 "nazwa własna": {"pos": "name"},

80 "rzeczownik odczasownikowy": {

81 "pos": "verb",

82 "tags": ["participle", "gerund"],

83 },

84}

86# Category:Proverb Templates

87# https://pl.wiktionary.org/wiki/Kategoria:Szablony_przysłów

88POS_PREFIXES = {

89 "przysłowie": {"pos": "proverb"},

90 "sentencja": {"pos": "phrase"},

91}

93IGNORE_POS_LINE_TEXT = frozenset(["rodzaj", "lub"])

96def extract_pos_section(

97 wxr: WiktextractContext,

98 page_data: list[WordEntry],

99 base_data: WordEntry,

100 level_node: LevelNode,

101) -> None:

102 has_pos = False

103 last_node_is_list = True

104 for node in level_node.find_child(NodeKind.ITALIC | NodeKind.LIST):

105 if node.kind == NodeKind.ITALIC:

106 if last_node_is_list:

107 new_has_pos = process_pos_line_italic_node(

108 wxr, page_data, base_data, node

109 )

110 if new_has_pos: 110 ↛ 112line 110 didn't jump to line 112 because the condition on line 110 was always true

111 has_pos = True

112 last_node_is_list = False

113 elif node.kind == NodeKind.LIST: 113 ↛ 104line 113 didn't jump to line 104 because the condition on line 113 was always true

114 if not has_pos:

115 page_data.append(base_data.model_copy(deep=True))

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

117 process_gloss_list_item(wxr, page_data[-1], list_item)

118 last_node_is_list = True

119

120

121def process_pos_line_italic_node(

122 wxr: WiktextractContext,

123 page_data: list[WordEntry],

124 base_data: WordEntry,

125 italic_node: WikiNode,

126) -> bool:

127 has_pos = False

128 page_data.append(base_data.model_copy(deep=True))

129 for child in italic_node.children:

130 if isinstance(child, TemplateNode):

131 child_text = clean_node(wxr, page_data[-1], child)

132 if child.template_name.startswith("forma "): 132 ↛ 140line 132 didn't jump to line 140 because the condition on line 132 was always true

133 # inflection form header templates

134 # https://pl.wiktionary.org/wiki/Kategoria:Szablony_nagłówków_form_fleksyjnych

135 pos_text = child_text.split(", ")[0]

136 if pos_text in POS_DATA: 136 ↛ 139line 136 didn't jump to line 139 because the condition on line 136 was always true

137 update_pos_data(page_data[-1], pos_text, POS_DATA[pos_text])

138 has_pos = True

139 page_data[-1].tags.append("form-of")

140 elif child_text in POS_DATA:

141 update_pos_data(page_data[-1], child_text, POS_DATA[child_text])

142 has_pos = True

143 else:

144 for prefix, pos_data in POS_PREFIXES.items():

145 if child_text.startswith(prefix):

146 update_pos_data(page_data[-1], child_text, pos_data)

147 has_pos = True

148 break

149 if not has_pos:

150 for text in child_text.split():

151 if text in POS_DATA:

152 update_pos_data(page_data[-1], text, POS_DATA[text])

153 has_pos = True

154 break

155 if not has_pos and child_text not in IGNORE_POS_LINE_TEXT:

156 page_data[-1].raw_tags.append(child_text)

157 elif isinstance(child, str): 157 ↛ 129line 157 didn't jump to line 129 because the condition on line 157 was always true

158 if child.strip() in POS_DATA:

159 child = child.strip()

160 update_pos_data(page_data[-1], child, POS_DATA[child])

161 has_pos = True

162 else:

163 for text in child.strip(", ").split(","):

164 text = text.strip()

165 if text in POS_DATA:

166 update_pos_data(page_data[-1], text, POS_DATA[text])

167 has_pos = True

168 elif text in TAGS: 168 ↛ 169line 168 didn't jump to line 169 because the condition on line 168 was never true

169 page_data[-1].raw_tags.append(text)

170 else:

171 for t in text.split():

172 if t in POS_DATA:

173 update_pos_data(page_data[-1], t, POS_DATA[t])

174 has_pos = True

175 elif t not in IGNORE_POS_LINE_TEXT:

176 page_data[-1].raw_tags.append(t)

177 translate_raw_tags(page_data[-1])

178 if not has_pos: 178 ↛ 179line 178 didn't jump to line 179 because the condition on line 178 was never true

179 page_data.pop()

180 return has_pos

181

182

183def update_pos_data(

184 word_entry: WordEntry, pos_text: str, pos_data: dict

185) -> None:

186 word_entry.pos = pos_data["pos"]

187 word_entry.tags.extend(pos_data.get("tags", []))

188 word_entry.pos_text = pos_text

189

190

191def process_gloss_list_item(

192 wxr: WiktextractContext, word_entry: WordEntry, list_item_node: WikiNode

193) -> None:

194 sense = Sense()

195 gloss_nodes = []

196 raw_tags = []

197 for gloss_node in list_item_node.children:

198 if isinstance(gloss_node, TemplateNode):

199 if gloss_node.template_name == "wikipedia":

200 continue

201 process_form_of_template(wxr, sense, gloss_node)

202 expanded_node = wxr.wtp.parse(

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

204 )

205 expanded_text = clean_node(wxr, sense, expanded_node.children)

206 if (

207 expanded_text.endswith(".")

208 and len(gloss_node.template_parameters) == 0

209 ):

210 # https://pl.wiktionary.org/wiki/Pomoc:Skróty_używane_w_Wikisłowniku

211 raw_tags.append(expanded_text)

212 else:

213 gloss_nodes.extend(expanded_node.children)

214 else:

215 gloss_nodes.append(gloss_node)

216 gloss_text = clean_node(wxr, sense, gloss_nodes)

217 m = re.match(r"\(\d+\.\d+\)", gloss_text)

218 sense_index = ""

219 if m is not None: 219 ↛ 222line 219 didn't jump to line 222 because the condition on line 219 was always true

220 sense_index = m.group(0).strip("()")

221 gloss_text = gloss_text[m.end() :].strip("=; ")

222 if "form-of" in word_entry.tags and len(sense.form_of) == 0:

223 form_of = ""

224 for node in gloss_nodes:

225 if isinstance(node, WikiNode) and node.kind == NodeKind.LINK:

226 form_of = clean_node(wxr, None, node)

227 if len(form_of) > 0: 227 ↛ 229line 227 didn't jump to line 229 because the condition on line 227 was always true

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

229 if len(gloss_text) > 0: 229 ↛ exitline 229 didn't return from function 'process_gloss_list_item' because the condition on line 229 was always true

230 sense.raw_tags = raw_tags

231 sense.sense_index = sense_index

232 sense.glosses.append(gloss_text)

233 translate_raw_tags(sense)

234 word_entry.senses.append(sense)

235

236

237def process_form_of_template(

238 wxr: WiktextractContext, sense: Sense, template_node: TemplateNode

239) -> None:

240 if template_node.template_name == "zob-ekwiw-pupr":

241 if "form-of" not in sense.tags: 241 ↛ 243line 241 didn't jump to line 243 because the condition on line 241 was always true

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

243 word = clean_node(

244 wxr, None, template_node.template_parameters.get(1, "")

245 )

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