@tricoteuses/senat 2.21.6 → 2.22.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (131) hide show
  1. package/lib/src/types/texte.d.ts +2 -5
  2. package/lib/src/types/texte.js +0 -1
  3. package/package.json +1 -1
  4. package/lib/config.d.ts +0 -3
  5. package/lib/config.js +0 -16
  6. package/lib/databases.d.ts +0 -2
  7. package/lib/databases.js +0 -26
  8. package/lib/datasets.d.ts +0 -34
  9. package/lib/datasets.js +0 -233
  10. package/lib/git.d.ts +0 -26
  11. package/lib/git.js +0 -167
  12. package/lib/index.d.ts +0 -13
  13. package/lib/index.js +0 -1
  14. package/lib/loaders.d.ts +0 -58
  15. package/lib/loaders.js +0 -286
  16. package/lib/model/agenda.d.ts +0 -6
  17. package/lib/model/agenda.js +0 -148
  18. package/lib/model/ameli.d.ts +0 -51
  19. package/lib/model/ameli.js +0 -149
  20. package/lib/model/commission.d.ts +0 -18
  21. package/lib/model/commission.js +0 -269
  22. package/lib/model/debats.d.ts +0 -67
  23. package/lib/model/debats.js +0 -95
  24. package/lib/model/documents.d.ts +0 -12
  25. package/lib/model/documents.js +0 -151
  26. package/lib/model/dosleg.d.ts +0 -7
  27. package/lib/model/dosleg.js +0 -326
  28. package/lib/model/index.d.ts +0 -7
  29. package/lib/model/index.js +0 -7
  30. package/lib/model/questions.d.ts +0 -45
  31. package/lib/model/questions.js +0 -89
  32. package/lib/model/scrutins.d.ts +0 -13
  33. package/lib/model/scrutins.js +0 -114
  34. package/lib/model/seance.d.ts +0 -3
  35. package/lib/model/seance.js +0 -267
  36. package/lib/model/sens.d.ts +0 -146
  37. package/lib/model/sens.js +0 -454
  38. package/lib/model/texte.d.ts +0 -7
  39. package/lib/model/texte.js +0 -228
  40. package/lib/model/util.d.ts +0 -9
  41. package/lib/model/util.js +0 -38
  42. package/lib/parsers/texte.d.ts +0 -7
  43. package/lib/parsers/texte.js +0 -228
  44. package/lib/raw_types/ameli.d.ts +0 -914
  45. package/lib/raw_types/ameli.js +0 -5
  46. package/lib/raw_types/debats.d.ts +0 -207
  47. package/lib/raw_types/debats.js +0 -5
  48. package/lib/raw_types/dosleg.d.ts +0 -1619
  49. package/lib/raw_types/dosleg.js +0 -5
  50. package/lib/raw_types/questions.d.ts +0 -419
  51. package/lib/raw_types/questions.js +0 -5
  52. package/lib/raw_types/senat.d.ts +0 -11368
  53. package/lib/raw_types/senat.js +0 -5
  54. package/lib/raw_types/sens.d.ts +0 -8248
  55. package/lib/raw_types/sens.js +0 -5
  56. package/lib/raw_types_schemats/ameli.d.ts +0 -539
  57. package/lib/raw_types_schemats/ameli.js +0 -2
  58. package/lib/raw_types_schemats/debats.d.ts +0 -127
  59. package/lib/raw_types_schemats/debats.js +0 -2
  60. package/lib/raw_types_schemats/dosleg.d.ts +0 -977
  61. package/lib/raw_types_schemats/dosleg.js +0 -2
  62. package/lib/raw_types_schemats/questions.d.ts +0 -235
  63. package/lib/raw_types_schemats/questions.js +0 -2
  64. package/lib/raw_types_schemats/sens.d.ts +0 -6915
  65. package/lib/raw_types_schemats/sens.js +0 -2
  66. package/lib/scripts/convert_data.d.ts +0 -1
  67. package/lib/scripts/convert_data.js +0 -354
  68. package/lib/scripts/data-download.d.ts +0 -1
  69. package/lib/scripts/data-download.js +0 -12
  70. package/lib/scripts/datautil.d.ts +0 -8
  71. package/lib/scripts/datautil.js +0 -34
  72. package/lib/scripts/parse_textes.d.ts +0 -1
  73. package/lib/scripts/parse_textes.js +0 -44
  74. package/lib/scripts/retrieve_agenda.d.ts +0 -1
  75. package/lib/scripts/retrieve_agenda.js +0 -132
  76. package/lib/scripts/retrieve_cr_commission.d.ts +0 -1
  77. package/lib/scripts/retrieve_cr_commission.js +0 -364
  78. package/lib/scripts/retrieve_cr_seance.d.ts +0 -6
  79. package/lib/scripts/retrieve_cr_seance.js +0 -347
  80. package/lib/scripts/retrieve_documents.d.ts +0 -3
  81. package/lib/scripts/retrieve_documents.js +0 -219
  82. package/lib/scripts/retrieve_open_data.d.ts +0 -1
  83. package/lib/scripts/retrieve_open_data.js +0 -315
  84. package/lib/scripts/retrieve_senateurs_photos.d.ts +0 -1
  85. package/lib/scripts/retrieve_senateurs_photos.js +0 -147
  86. package/lib/scripts/retrieve_videos.d.ts +0 -1
  87. package/lib/scripts/retrieve_videos.js +0 -461
  88. package/lib/scripts/shared/cli_helpers.d.ts +0 -95
  89. package/lib/scripts/shared/cli_helpers.js +0 -91
  90. package/lib/scripts/shared/util.d.ts +0 -4
  91. package/lib/scripts/shared/util.js +0 -35
  92. package/lib/scripts/test_iter_load.d.ts +0 -1
  93. package/lib/scripts/test_iter_load.js +0 -12
  94. package/lib/strings.d.ts +0 -1
  95. package/lib/strings.js +0 -18
  96. package/lib/types/agenda.d.ts +0 -44
  97. package/lib/types/agenda.js +0 -1
  98. package/lib/types/ameli.d.ts +0 -5
  99. package/lib/types/ameli.js +0 -1
  100. package/lib/types/compte_rendu.d.ts +0 -83
  101. package/lib/types/compte_rendu.js +0 -1
  102. package/lib/types/debats.d.ts +0 -2
  103. package/lib/types/debats.js +0 -1
  104. package/lib/types/dosleg.d.ts +0 -70
  105. package/lib/types/dosleg.js +0 -1
  106. package/lib/types/questions.d.ts +0 -2
  107. package/lib/types/questions.js +0 -1
  108. package/lib/types/sens.d.ts +0 -10
  109. package/lib/types/sens.js +0 -1
  110. package/lib/types/sessions.d.ts +0 -5
  111. package/lib/types/sessions.js +0 -84
  112. package/lib/types/texte.d.ts +0 -74
  113. package/lib/types/texte.js +0 -16
  114. package/lib/utils/cr_spliting.d.ts +0 -28
  115. package/lib/utils/cr_spliting.js +0 -265
  116. package/lib/utils/date.d.ts +0 -10
  117. package/lib/utils/date.js +0 -100
  118. package/lib/utils/nvs-timecode.d.ts +0 -7
  119. package/lib/utils/nvs-timecode.js +0 -79
  120. package/lib/utils/reunion_grouping.d.ts +0 -11
  121. package/lib/utils/reunion_grouping.js +0 -337
  122. package/lib/utils/reunion_odj_building.d.ts +0 -5
  123. package/lib/utils/reunion_odj_building.js +0 -154
  124. package/lib/utils/reunion_parsing.d.ts +0 -23
  125. package/lib/utils/reunion_parsing.js +0 -209
  126. package/lib/utils/scoring.d.ts +0 -14
  127. package/lib/utils/scoring.js +0 -147
  128. package/lib/utils/string_cleaning.d.ts +0 -7
  129. package/lib/utils/string_cleaning.js +0 -57
  130. package/lib/validators/config.d.ts +0 -1
  131. package/lib/validators/config.js +0 -54
@@ -1,228 +0,0 @@
1
- import { JSDOM } from "jsdom";
2
- import { AKN_IDENTIFICATION_STRUCTURE_REGEXP, AKN_WORKFLOW_IDENTIFICATION_STRUCTURE_REGEXP } from "../scripts/datautil";
3
- import { DivisionType, } from "../types/texte";
4
- function buildWorklow(metaElement) {
5
- const stepElements = metaElement.querySelectorAll("workflow step");
6
- const steps = [];
7
- for (const stepElement of stepElements) {
8
- const identification = stepElement.getAttribute("href") ?? "";
9
- const identificationParts = AKN_WORKFLOW_IDENTIFICATION_STRUCTURE_REGEXP.exec(identification)?.groups;
10
- steps.push({
11
- eId: stepElement.getAttribute("eId"),
12
- date: stepElement.getAttribute("date") ? new Date(stepElement.getAttribute("date") ?? "") : null,
13
- type: identificationParts?.["type"] || null,
14
- session: identificationParts?.["session"] || null,
15
- numero: identificationParts?.["numTexte"] || null,
16
- version: identificationParts?.["version"] ? identificationParts["version"] : null,
17
- outcome: stepElement.getAttribute("outcome"),
18
- });
19
- }
20
- return steps;
21
- }
22
- function buildDivision(node, index) {
23
- const eId = node.getAttribute("eId");
24
- const tag = node.nodeName;
25
- const level = DivisionType[tag];
26
- const titleNode = node.querySelector("num");
27
- const subtitleNode = node.querySelector("heading");
28
- const headings = [
29
- ...(titleNode
30
- ? [
31
- {
32
- text: titleNode.textContent?.trim() ?? null,
33
- html: titleNode.innerHTML?.trim() ?? null,
34
- },
35
- ]
36
- : []),
37
- ...(subtitleNode
38
- ? [
39
- {
40
- text: subtitleNode.textContent?.trim() ?? null,
41
- html: subtitleNode.innerHTML?.trim() ?? null,
42
- },
43
- ]
44
- : []),
45
- ];
46
- const division = {
47
- index,
48
- eId,
49
- tag,
50
- level,
51
- headings,
52
- };
53
- if (tag === "article") {
54
- ;
55
- division.alineas = [];
56
- }
57
- return division;
58
- }
59
- function buildAlinea(contentNode, alineaNode) {
60
- const eId = alineaNode.getAttribute("eId");
61
- const heading = {
62
- text: alineaNode.querySelector("num")?.textContent ?? null,
63
- };
64
- const pastille = alineaNode.getAttribute("data:pastille") ?? null;
65
- return {
66
- eId,
67
- heading,
68
- text: contentNode.textContent?.trim() ?? null,
69
- html: contentNode.innerHTML?.trim() ?? null,
70
- pastille,
71
- };
72
- }
73
- function buildEmptyArticle(index) {
74
- return {
75
- index: index,
76
- eId: "",
77
- tag: "article",
78
- level: DivisionType["article"],
79
- headings: [],
80
- alineas: [],
81
- };
82
- }
83
- function flattenTexte(texteContentRoot) {
84
- const divisions = [];
85
- let divisionIndex = 0;
86
- const iter = (node) => {
87
- if (node.nodeName === "content") {
88
- return;
89
- }
90
- switch (node.nodeName) {
91
- case "tome":
92
- case "part":
93
- case "book":
94
- case "title":
95
- case "subtitle":
96
- case "chapter":
97
- case "section":
98
- case "subsection":
99
- case "paragraph":
100
- case "article":
101
- divisions.push(buildDivision(node, divisionIndex++));
102
- break;
103
- }
104
- if (node.nodeName === "alinea") {
105
- Array.from(node.childNodes)
106
- // Find direct content children programmatically
107
- // because `:scope` selector does not work
108
- // https://github.com/jsdom/jsdom/issues/2998
109
- .filter((alineaChildNode) => alineaChildNode.nodeName === "content")
110
- .forEach((alineaContentNode) => {
111
- // Hypothesis: alineas should always be enclosed in articles
112
- let lastArticle = divisions.findLast((division) => division.tag === "article");
113
- if (!lastArticle) {
114
- lastArticle = buildEmptyArticle(divisionIndex++);
115
- divisions.push(lastArticle);
116
- }
117
- lastArticle.alineas.push(buildAlinea(alineaContentNode, node));
118
- });
119
- }
120
- if (node.hasChildNodes()) {
121
- node.childNodes.forEach((childNode) => iter(childNode));
122
- }
123
- };
124
- iter(texteContentRoot);
125
- return divisions;
126
- }
127
- export function transformTexte(document) {
128
- const metaElement = document.querySelector("meta");
129
- const preambleElement = document.querySelector("preamble");
130
- const identification = metaElement?.querySelector("FRBRExpression FRBRuri")?.getAttribute("value") ?? "";
131
- const identificationParts = AKN_IDENTIFICATION_STRUCTURE_REGEXP.exec(identification)?.groups;
132
- const bodyElement = document.querySelector("body");
133
- const sessionYears = identificationParts?.["session"]?.split("-") || null;
134
- const datePresentation = metaElement?.querySelector("FRBRdate[name='#presentation']")?.getAttribute("date");
135
- const dateDepot = metaElement?.querySelector("FRBRdate[name='#depot']")?.getAttribute("date");
136
- const datePublicationXml = metaElement?.querySelector("FRBRdate[name='#publication-xml']")?.getAttribute("date");
137
- return {
138
- titre: preambleElement?.querySelector("docTitle")?.textContent || null,
139
- titreCourt: metaElement?.querySelector("FRBRalias[name='intitule-court']")?.getAttribute("value") || null,
140
- signetDossier: metaElement?.querySelector("FRBRalias[name='signet-dossier-legislatif-senat']")?.getAttribute("value") || null,
141
- urlDossierSenat: metaElement?.querySelector("FRBRalias[name='url-senat']")?.getAttribute("value") || null,
142
- urlDossierAssemblee: metaElement?.querySelector("FRBRalias[name='url-AN']")?.getAttribute("value") || null,
143
- type: identificationParts?.["type"] || null,
144
- session: sessionYears && sessionYears.length > 0 ? sessionYears[0] : null,
145
- numero: identificationParts?.["numTexte"] ? parseInt(identificationParts["numTexte"]) : null,
146
- datePresentation: datePresentation ? new Date(datePresentation) : null,
147
- dateDepot: dateDepot ? new Date(dateDepot) : null,
148
- datePublicationXml: datePublicationXml ? new Date(datePublicationXml) : null,
149
- version: identificationParts?.["version"] ? identificationParts["version"] : null,
150
- workflow: metaElement ? buildWorklow(metaElement) : [],
151
- divisions: bodyElement ? flattenTexte(bodyElement) : [],
152
- };
153
- }
154
- export function transformExposeDesMotifs(document) {
155
- const sectionElements = document.querySelectorAll("section");
156
- const exposeDesMotifsRegexp = new RegExp("EXPOS.{1,2}[\\n\\s]DES[\\n\\s]MOTIFS");
157
- for (const sectionElement of sectionElements) {
158
- const firstParagraph = sectionElement.querySelector("p:first-of-type");
159
- const secondParagraph = sectionElement.querySelector("p:nth-of-type(2)");
160
- if (!firstParagraph) {
161
- continue;
162
- }
163
- const firstParagraphContent = firstParagraph.textContent;
164
- const secondParagraphContent = secondParagraph?.textContent;
165
- if (!firstParagraphContent || !exposeDesMotifsRegexp.test(firstParagraphContent.toUpperCase())) {
166
- if (!secondParagraphContent || !exposeDesMotifsRegexp.test(secondParagraphContent.toUpperCase())) {
167
- continue;
168
- }
169
- else {
170
- secondParagraph.remove();
171
- }
172
- }
173
- firstParagraph.remove();
174
- return {
175
- text: sectionElement.textContent?.trim() ?? null,
176
- html: sectionElement.innerHTML?.trim() ?? null,
177
- };
178
- }
179
- return null;
180
- }
181
- export function parseTexte(texteXml) {
182
- try {
183
- const { document } = new JSDOM(texteXml, {
184
- contentType: "text/xml",
185
- }).window;
186
- return transformTexte(document);
187
- }
188
- catch (error) {
189
- console.error(`Could not parse texte with error ${error}`);
190
- }
191
- return null;
192
- }
193
- // Prevent from memory leak
194
- // https://github.com/jsdom/jsdom/issues/2583#issuecomment-559520814
195
- export async function parseTexteFromFile(xmlFilePath) {
196
- try {
197
- const { document } = (await JSDOM.fromFile(xmlFilePath, { contentType: "text/xml" })).window;
198
- return transformTexte(document);
199
- }
200
- catch (error) {
201
- console.error(`Could not parse texte with error ${error}`);
202
- }
203
- return null;
204
- }
205
- export function parseExposeDesMotifs(exposeDesMotifsHtml) {
206
- try {
207
- const { document } = new JSDOM(exposeDesMotifsHtml, {
208
- contentType: "text/html",
209
- }).window;
210
- return transformExposeDesMotifs(document);
211
- }
212
- catch (error) {
213
- console.error(`Could not parse exposé des motifs with error ${error}`);
214
- }
215
- return null;
216
- }
217
- // Prevent from memory leak
218
- // https://github.com/jsdom/jsdom/issues/2583#issuecomment-559520814
219
- export async function parseExposeDesMotifsFromFile(htmlFilePath) {
220
- try {
221
- const { document } = (await JSDOM.fromFile(htmlFilePath, { contentType: "text/html" })).window;
222
- return transformExposeDesMotifs(document);
223
- }
224
- catch (error) {
225
- console.error(`Could not parse exposé des motifs with error ${error}`);
226
- }
227
- return null;
228
- }
@@ -1,9 +0,0 @@
1
- import { Expression } from "kysely";
2
- export declare function concat(...exprs: Expression<number | string | null | undefined>[]): import("kysely").RawBuilder<string>;
3
- export declare function expandToRows(expr: Expression<string | null | undefined>, regexp: Expression<string>): import("kysely").RawBuilder<unknown>;
4
- export declare function nullIf(expr: Expression<number | string | null | undefined>): import("kysely").RawBuilder<unknown>;
5
- export declare function removeSubstring(expr: Expression<string | null | undefined>, pattern: Expression<string>): import("kysely").RawBuilder<string>;
6
- export declare function replace(expr: Expression<string | null | undefined>, pattern: Expression<string>, replacement: Expression<string>): import("kysely").RawBuilder<string>;
7
- export declare function rtrim(expr: Expression<string | null | undefined>): import("kysely").RawBuilder<string>;
8
- export declare function toDateString(expr: Expression<Date | null | undefined>, format?: Expression<string>): import("kysely").RawBuilder<string>;
9
- export declare function toCRDate(dateISO: string, startTime?: string | null): string;
package/lib/model/util.js DELETED
@@ -1,38 +0,0 @@
1
- import { sql } from "kysely";
2
- import { STANDARD_DATE_FORMAT } from "../scripts/datautil";
3
- export function concat(...exprs) {
4
- return sql.join(exprs, sql `||`).$castTo();
5
- }
6
- export function expandToRows(expr, regexp) {
7
- return sql `unnest(regexp_matches(${expr}, ${regexp}, 'g'))`;
8
- }
9
- export function nullIf(expr) {
10
- return sql `nullif(trim(${expr}), '')`;
11
- }
12
- export function removeSubstring(expr, pattern) {
13
- return replace(expr, pattern, sql.val(""));
14
- }
15
- export function replace(expr, pattern, replacement) {
16
- return sql `replace(${expr}, ${pattern}, ${replacement})`;
17
- }
18
- export function rtrim(expr) {
19
- return sql `rtrim(${expr})`;
20
- }
21
- export function toDateString(expr, format = sql.val(STANDARD_DATE_FORMAT)) {
22
- return sql `to_char(${expr}, ${format})`;
23
- }
24
- export function toCRDate(dateISO, startTime) {
25
- const yyyymmdd = dateISO.replace(/-/g, ""); // "20250716"
26
- let hh = "00", mm = "00", ss = "00", SSS = "000";
27
- if (startTime) {
28
- // accepte "HH:MM:SS", "HH:MM:SS.mmm", "HH:MM:SS.mmm+02:00"
29
- const m = startTime.match(/(\d{2}):(\d{2}):(\d{2})(?:\.(\d{3}))?/);
30
- if (m) {
31
- hh = m[1];
32
- mm = m[2];
33
- ss = m[3];
34
- SSS = m[4] || "000";
35
- }
36
- }
37
- return `${yyyymmdd}${hh}${mm}${ss}${SSS}`;
38
- }
@@ -1,7 +0,0 @@
1
- import { ExposeDesMotifs, FlatTexte } from "../types/texte";
2
- export declare function transformTexte(document: Document): FlatTexte | null;
3
- export declare function transformExposeDesMotifs(document: Document): ExposeDesMotifs | null;
4
- export declare function parseTexte(texteXml: string): FlatTexte | null;
5
- export declare function parseTexteFromFile(xmlFilePath: string): Promise<FlatTexte | null>;
6
- export declare function parseExposeDesMotifs(exposeDesMotifsHtml: string): ExposeDesMotifs | null;
7
- export declare function parseExposeDesMotifsFromFile(htmlFilePath: string): Promise<ExposeDesMotifs | null>;
@@ -1,228 +0,0 @@
1
- import { JSDOM } from "jsdom";
2
- import { AKN_IDENTIFICATION_STRUCTURE_REGEXP, AKN_WORKFLOW_IDENTIFICATION_STRUCTURE_REGEXP } from "../scripts/datautil";
3
- import { DivisionType, } from "../types/texte";
4
- function buildWorklow(metaElement) {
5
- const stepElements = metaElement.querySelectorAll("workflow step");
6
- const steps = [];
7
- for (const stepElement of stepElements) {
8
- const identification = stepElement.getAttribute("href") ?? "";
9
- const identificationParts = AKN_WORKFLOW_IDENTIFICATION_STRUCTURE_REGEXP.exec(identification)?.groups;
10
- steps.push({
11
- eId: stepElement.getAttribute("eId"),
12
- date: stepElement.getAttribute("date") ? new Date(stepElement.getAttribute("date") ?? "") : null,
13
- type: identificationParts?.["type"] || null,
14
- session: identificationParts?.["session"] || null,
15
- numero: identificationParts?.["numTexte"] || null,
16
- version: identificationParts?.["version"] ? identificationParts["version"] : null,
17
- outcome: stepElement.getAttribute("outcome"),
18
- });
19
- }
20
- return steps;
21
- }
22
- function buildDivision(node, index) {
23
- const eId = node.getAttribute("eId");
24
- const tag = node.nodeName;
25
- const level = DivisionType[tag];
26
- const titleNode = node.querySelector("num");
27
- const subtitleNode = node.querySelector("heading");
28
- const headings = [
29
- ...(titleNode
30
- ? [
31
- {
32
- text: titleNode.textContent?.trim() ?? null,
33
- html: titleNode.innerHTML?.trim() ?? null,
34
- },
35
- ]
36
- : []),
37
- ...(subtitleNode
38
- ? [
39
- {
40
- text: subtitleNode.textContent?.trim() ?? null,
41
- html: subtitleNode.innerHTML?.trim() ?? null,
42
- },
43
- ]
44
- : []),
45
- ];
46
- const division = {
47
- index,
48
- eId,
49
- tag,
50
- level,
51
- headings,
52
- };
53
- if (tag === "article") {
54
- ;
55
- division.alineas = [];
56
- }
57
- return division;
58
- }
59
- function buildAlinea(contentNode, alineaNode) {
60
- const eId = alineaNode.getAttribute("eId");
61
- const heading = {
62
- text: alineaNode.querySelector("num")?.textContent ?? null,
63
- };
64
- const pastille = alineaNode.getAttribute("data:pastille") ?? null;
65
- return {
66
- eId,
67
- heading,
68
- text: contentNode.textContent?.trim() ?? null,
69
- html: contentNode.innerHTML?.trim() ?? null,
70
- pastille,
71
- };
72
- }
73
- function buildEmptyArticle(index) {
74
- return {
75
- index: index,
76
- eId: "",
77
- tag: "article",
78
- level: DivisionType["article"],
79
- headings: [],
80
- alineas: [],
81
- };
82
- }
83
- function flattenTexte(texteContentRoot) {
84
- const divisions = [];
85
- let divisionIndex = 0;
86
- const iter = (node) => {
87
- if (node.nodeName === "content") {
88
- return;
89
- }
90
- switch (node.nodeName) {
91
- case "tome":
92
- case "part":
93
- case "book":
94
- case "title":
95
- case "subtitle":
96
- case "chapter":
97
- case "section":
98
- case "subsection":
99
- case "paragraph":
100
- case "article":
101
- divisions.push(buildDivision(node, divisionIndex++));
102
- break;
103
- }
104
- if (node.nodeName === "alinea") {
105
- Array.from(node.childNodes)
106
- // Find direct content children programmatically
107
- // because `:scope` selector does not work
108
- // https://github.com/jsdom/jsdom/issues/2998
109
- .filter((alineaChildNode) => alineaChildNode.nodeName === "content")
110
- .forEach((alineaContentNode) => {
111
- // Hypothesis: alineas should always be enclosed in articles
112
- let lastArticle = divisions.findLast((division) => division.tag === "article");
113
- if (!lastArticle) {
114
- lastArticle = buildEmptyArticle(divisionIndex++);
115
- divisions.push(lastArticle);
116
- }
117
- lastArticle.alineas.push(buildAlinea(alineaContentNode, node));
118
- });
119
- }
120
- if (node.hasChildNodes()) {
121
- node.childNodes.forEach((childNode) => iter(childNode));
122
- }
123
- };
124
- iter(texteContentRoot);
125
- return divisions;
126
- }
127
- export function transformTexte(document) {
128
- const metaElement = document.querySelector("meta");
129
- const preambleElement = document.querySelector("preamble");
130
- const identification = metaElement?.querySelector("FRBRExpression FRBRuri")?.getAttribute("value") ?? "";
131
- const identificationParts = AKN_IDENTIFICATION_STRUCTURE_REGEXP.exec(identification)?.groups;
132
- const bodyElement = document.querySelector("body");
133
- const sessionYears = identificationParts?.["session"]?.split("-") || null;
134
- const datePresentation = metaElement?.querySelector("FRBRdate[name='#presentation']")?.getAttribute("date");
135
- const dateDepot = metaElement?.querySelector("FRBRdate[name='#depot']")?.getAttribute("date");
136
- const datePublicationXml = metaElement?.querySelector("FRBRdate[name='#publication-xml']")?.getAttribute("date");
137
- return {
138
- titre: preambleElement?.querySelector("docTitle")?.textContent || null,
139
- titreCourt: metaElement?.querySelector("FRBRalias[name='intitule-court']")?.getAttribute("value") || null,
140
- signetDossier: metaElement?.querySelector("FRBRalias[name='signet-dossier-legislatif-senat']")?.getAttribute("value") || null,
141
- urlDossierSenat: metaElement?.querySelector("FRBRalias[name='url-senat']")?.getAttribute("value") || null,
142
- urlDossierAssemblee: metaElement?.querySelector("FRBRalias[name='url-AN']")?.getAttribute("value") || null,
143
- type: identificationParts?.["type"] || null,
144
- session: sessionYears && sessionYears.length > 0 ? sessionYears[0] : null,
145
- numero: identificationParts?.["numTexte"] ? parseInt(identificationParts["numTexte"]) : null,
146
- datePresentation: datePresentation ? new Date(datePresentation) : null,
147
- dateDepot: dateDepot ? new Date(dateDepot) : null,
148
- datePublicationXml: datePublicationXml ? new Date(datePublicationXml) : null,
149
- version: identificationParts?.["version"] ? identificationParts["version"] : null,
150
- workflow: metaElement ? buildWorklow(metaElement) : [],
151
- divisions: bodyElement ? flattenTexte(bodyElement) : [],
152
- };
153
- }
154
- export function transformExposeDesMotifs(document) {
155
- const sectionElements = document.querySelectorAll("section");
156
- const exposeDesMotifsRegexp = new RegExp("EXPOS.{1,2}[\\n\\s]DES[\\n\\s]MOTIFS");
157
- for (const sectionElement of sectionElements) {
158
- const firstParagraph = sectionElement.querySelector("p:first-of-type");
159
- const secondParagraph = sectionElement.querySelector("p:nth-of-type(2)");
160
- if (!firstParagraph) {
161
- continue;
162
- }
163
- const firstParagraphContent = firstParagraph.textContent;
164
- const secondParagraphContent = secondParagraph?.textContent;
165
- if (!firstParagraphContent || !exposeDesMotifsRegexp.test(firstParagraphContent.toUpperCase())) {
166
- if (!secondParagraphContent || !exposeDesMotifsRegexp.test(secondParagraphContent.toUpperCase())) {
167
- continue;
168
- }
169
- else {
170
- secondParagraph.remove();
171
- }
172
- }
173
- firstParagraph.remove();
174
- return {
175
- text: sectionElement.textContent?.trim() ?? null,
176
- html: sectionElement.innerHTML?.trim() ?? null,
177
- };
178
- }
179
- return null;
180
- }
181
- export function parseTexte(texteXml) {
182
- try {
183
- const { document } = new JSDOM(texteXml, {
184
- contentType: "text/xml",
185
- }).window;
186
- return transformTexte(document);
187
- }
188
- catch (error) {
189
- console.error(`Could not parse texte with error ${error}`);
190
- }
191
- return null;
192
- }
193
- // Prevent from memory leak
194
- // https://github.com/jsdom/jsdom/issues/2583#issuecomment-559520814
195
- export async function parseTexteFromFile(xmlFilePath) {
196
- try {
197
- const { document } = (await JSDOM.fromFile(xmlFilePath, { contentType: "text/xml" })).window;
198
- return transformTexte(document);
199
- }
200
- catch (error) {
201
- console.error(`Could not parse texte with error ${error}`);
202
- }
203
- return null;
204
- }
205
- export function parseExposeDesMotifs(exposeDesMotifsHtml) {
206
- try {
207
- const { document } = new JSDOM(exposeDesMotifsHtml, {
208
- contentType: "text/html",
209
- }).window;
210
- return transformExposeDesMotifs(document);
211
- }
212
- catch (error) {
213
- console.error(`Could not parse exposé des motifs with error ${error}`);
214
- }
215
- return null;
216
- }
217
- // Prevent from memory leak
218
- // https://github.com/jsdom/jsdom/issues/2583#issuecomment-559520814
219
- export async function parseExposeDesMotifsFromFile(htmlFilePath) {
220
- try {
221
- const { document } = (await JSDOM.fromFile(htmlFilePath, { contentType: "text/html" })).window;
222
- return transformExposeDesMotifs(document);
223
- }
224
- catch (error) {
225
- console.error(`Could not parse exposé des motifs with error ${error}`);
226
- }
227
- return null;
228
- }