From 472e5051554792dd95406f8a35dd81a428ad1d05 Mon Sep 17 00:00:00 2001
From: cboulanger <info@bibliograph.org>
Date: Mon, 29 Jul 2024 10:04:07 +0200
Subject: [PATCH] Add TEI tags documentation
---
convert-anystyle-data/anystyle-to-tei.ipynb | 105 ++++++++++--------
.../schema/tei-tags-documentation.json | 8 ++
2 files changed, 65 insertions(+), 48 deletions(-)
diff --git a/convert-anystyle-data/anystyle-to-tei.ipynb b/convert-anystyle-data/anystyle-to-tei.ipynb
index 02bf772..3c0758f 100644
--- a/convert-anystyle-data/anystyle-to-tei.ipynb
+++ b/convert-anystyle-data/anystyle-to-tei.ipynb
@@ -83,8 +83,7 @@
" bibl_schema = schema.find(\"tei:bibl\")\n",
" data_list = []\n",
" #names = [child_element.local_name for child_element in bibl_schema.iterchildren()]\n",
- " names = ['author', 'citedRange', 'date', 'edition', 'editor', 'location', 'note', 'publisher', 'pubPlace', 'series',\n",
- " 'span', 'title', 'volume', 'issue']\n",
+ " names = ['author', 'biblScope', 'citedRange', 'date', 'edition', 'editor', 'location', 'note', 'publisher', 'pubPlace', 'series', 'span', 'title', 'volume', 'issue']\n",
" for name in tqdm(names, desc=\"Processing TEI tags\"):\n",
" doc_node = root.find(f\".//xs:element[@name='{name}']/xs:annotation/xs:documentation\", namespaces=namespaces)\n",
" if doc_node is not None:\n",
@@ -98,7 +97,7 @@
" return pd.DataFrame(data_list)\n",
"\n",
"\n",
- "cache_file = \"schema/tei-tags-documentation.json\"\n",
+ "cache_file = \"schema/tei/tei-tags-documentation.json\"\n",
"if not os.path.isfile(cache_file):\n",
" df = generate_tag_docs(\"schema/tei/tei_all.xsd\")\n",
" df.to_json(cache_file, index=False, orient='records')\n",
@@ -109,8 +108,8 @@
"metadata": {
"collapsed": false,
"ExecuteTime": {
- "end_time": "2024-07-29T07:56:06.664531Z",
- "start_time": "2024-07-29T07:55:52.208162Z"
+ "end_time": "2024-07-29T08:03:30.899758Z",
+ "start_time": "2024-07-29T08:03:16.672095Z"
}
},
"id": "572f566fc9784238",
@@ -118,12 +117,12 @@
{
"data": {
"text/plain": [
- "Processing TEI tags: 0%| | 0/14 [00:00<?, ?it/s]"
+ "Processing TEI tags: 0%| | 0/15 [00:00<?, ?it/s]"
],
"application/vnd.jupyter.widget-view+json": {
"version_major": 2,
"version_minor": 0,
- "model_id": "517f81d06e204232823c4b049be3de46"
+ "model_id": "2b29eb53bd824a9e8ee692483a17d0da"
}
},
"metadata": {},
@@ -134,45 +133,48 @@
"text/plain": [
" name description \\\n",
"0 author (author) in a bibliographic reference, contain... \n",
- "1 citedRange (cited range) defines the range of cited conte... \n",
- "2 date (date) contains a date in any format. \n",
- "3 edition (edition) describes the particularities of one... \n",
- "4 editor contains a secondary statement of responsibili... \n",
- "5 location (location) defines the location of a place as ... \n",
- "6 note (note) contains a note or annotation. \n",
- "7 publisher (publisher) provides the name of the organizat... \n",
- "8 pubPlace (publication place) contains the name of the p... \n",
- "9 series (series information) contains information abou... \n",
- "10 span associates an interpretative annotation direct... \n",
- "11 title (title) contains a title for any kind of work. \n",
+ "1 biblScope (scope of bibliographic reference) defines the... \n",
+ "2 citedRange (cited range) defines the range of cited conte... \n",
+ "3 date (date) contains a date in any format. \n",
+ "4 edition (edition) describes the particularities of one... \n",
+ "5 editor contains a secondary statement of responsibili... \n",
+ "6 location (location) defines the location of a place as ... \n",
+ "7 note (note) contains a note or annotation. \n",
+ "8 publisher (publisher) provides the name of the organizat... \n",
+ "9 pubPlace (publication place) contains the name of the p... \n",
+ "10 series (series information) contains information abou... \n",
+ "11 span associates an interpretative annotation direct... \n",
+ "12 title (title) contains a title for any kind of work. \n",
"\n",
" documentation \\\n",
"0 3.12.2.2. Titles, Authors, and Editors 2.2.1. ... \n",
"1 3.12.2.5. Scopes and Ranges in Bibliographic C... \n",
- "2 3.6.4. Dates and Times 2.2.4. Publication, Dis... \n",
- "3 2.2.2. The Edition Statement \n",
- "4 3.12.2.2. Titles, Authors, and Editors \n",
- "5 14.3.4. Places \n",
- "6 3.9.1. Notes and Simple Annotation 2.2.6. The ... \n",
- "7 3.12.2.4. Imprint, Size of a Document, and Rep... \n",
+ "2 3.12.2.5. Scopes and Ranges in Bibliographic C... \n",
+ "3 3.6.4. Dates and Times 2.2.4. Publication, Dis... \n",
+ "4 2.2.2. The Edition Statement \n",
+ "5 3.12.2.2. Titles, Authors, and Editors \n",
+ "6 14.3.4. Places \n",
+ "7 3.9.1. Notes and Simple Annotation 2.2.6. The ... \n",
"8 3.12.2.4. Imprint, Size of a Document, and Rep... \n",
- "9 3.12.2.1. Analytic, Monographic, and Series Le... \n",
- "10 18.3. Spans and Interpretations \n",
- "11 3.12.2.2. Titles, Authors, and Editors 2.2.1. ... \n",
+ "9 3.12.2.4. Imprint, Size of a Document, and Rep... \n",
+ "10 3.12.2.1. Analytic, Monographic, and Series Le... \n",
+ "11 18.3. Spans and Interpretations \n",
+ "12 3.12.2.2. Titles, Authors, and Editors 2.2.1. ... \n",
"\n",
" urls \n",
"0 {'3.12.2.2': 'https://vault.tei-c.de/P5/3.0.0/... \n",
"1 {'3.12.2.5': 'https://vault.tei-c.de/P5/3.0.0/... \n",
- "2 {'3.6.4': 'https://vault.tei-c.de/P5/3.0.0/doc... \n",
- "3 {'2.2.2': 'https://vault.tei-c.de/P5/3.0.0/doc... \n",
- "4 {'3.12.2.2': 'https://vault.tei-c.de/P5/3.0.0/... \n",
- "5 {'14.3.4': 'https://vault.tei-c.de/P5/3.0.0/do... \n",
- "6 {'3.9.1': 'https://vault.tei-c.de/P5/3.0.0/doc... \n",
- "7 {'3.12.2.4': 'https://vault.tei-c.de/P5/3.0.0/... \n",
+ "2 {'3.12.2.5': 'https://vault.tei-c.de/P5/3.0.0/... \n",
+ "3 {'3.6.4': 'https://vault.tei-c.de/P5/3.0.0/doc... \n",
+ "4 {'2.2.2': 'https://vault.tei-c.de/P5/3.0.0/doc... \n",
+ "5 {'3.12.2.2': 'https://vault.tei-c.de/P5/3.0.0/... \n",
+ "6 {'14.3.4': 'https://vault.tei-c.de/P5/3.0.0/do... \n",
+ "7 {'3.9.1': 'https://vault.tei-c.de/P5/3.0.0/doc... \n",
"8 {'3.12.2.4': 'https://vault.tei-c.de/P5/3.0.0/... \n",
- "9 {'3.12.2.1': 'https://vault.tei-c.de/P5/3.0.0/... \n",
- "10 {'18.3': 'https://vault.tei-c.de/P5/3.0.0/doc/... \n",
- "11 {'3.12.2.2': 'https://vault.tei-c.de/P5/3.0.0/... "
+ "9 {'3.12.2.4': 'https://vault.tei-c.de/P5/3.0.0/... \n",
+ "10 {'3.12.2.1': 'https://vault.tei-c.de/P5/3.0.0/... \n",
+ "11 {'18.3': 'https://vault.tei-c.de/P5/3.0.0/doc/... \n",
+ "12 {'3.12.2.2': 'https://vault.tei-c.de/P5/3.0.0/... "
],
"text/html": [
"<div>\n",
@@ -209,76 +211,83 @@
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
+ " <td>biblScope</td>\n",
+ " <td>(scope of bibliographic reference) defines the...</td>\n",
+ " <td>3.12.2.5. Scopes and Ranges in Bibliographic C...</td>\n",
+ " <td>{'3.12.2.5': 'https://vault.tei-c.de/P5/3.0.0/...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
" <td>citedRange</td>\n",
" <td>(cited range) defines the range of cited conte...</td>\n",
" <td>3.12.2.5. Scopes and Ranges in Bibliographic C...</td>\n",
" <td>{'3.12.2.5': 'https://vault.tei-c.de/P5/3.0.0/...</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>2</th>\n",
+ " <th>3</th>\n",
" <td>date</td>\n",
" <td>(date) contains a date in any format.</td>\n",
" <td>3.6.4. Dates and Times 2.2.4. Publication, Dis...</td>\n",
" <td>{'3.6.4': 'https://vault.tei-c.de/P5/3.0.0/doc...</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>3</th>\n",
+ " <th>4</th>\n",
" <td>edition</td>\n",
" <td>(edition) describes the particularities of one...</td>\n",
" <td>2.2.2. The Edition Statement</td>\n",
" <td>{'2.2.2': 'https://vault.tei-c.de/P5/3.0.0/doc...</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>4</th>\n",
+ " <th>5</th>\n",
" <td>editor</td>\n",
" <td>contains a secondary statement of responsibili...</td>\n",
" <td>3.12.2.2. Titles, Authors, and Editors</td>\n",
" <td>{'3.12.2.2': 'https://vault.tei-c.de/P5/3.0.0/...</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>5</th>\n",
+ " <th>6</th>\n",
" <td>location</td>\n",
" <td>(location) defines the location of a place as ...</td>\n",
" <td>14.3.4. Places</td>\n",
" <td>{'14.3.4': 'https://vault.tei-c.de/P5/3.0.0/do...</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>6</th>\n",
+ " <th>7</th>\n",
" <td>note</td>\n",
" <td>(note) contains a note or annotation.</td>\n",
" <td>3.9.1. Notes and Simple Annotation 2.2.6. The ...</td>\n",
" <td>{'3.9.1': 'https://vault.tei-c.de/P5/3.0.0/doc...</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>7</th>\n",
+ " <th>8</th>\n",
" <td>publisher</td>\n",
" <td>(publisher) provides the name of the organizat...</td>\n",
" <td>3.12.2.4. Imprint, Size of a Document, and Rep...</td>\n",
" <td>{'3.12.2.4': 'https://vault.tei-c.de/P5/3.0.0/...</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>8</th>\n",
+ " <th>9</th>\n",
" <td>pubPlace</td>\n",
" <td>(publication place) contains the name of the p...</td>\n",
" <td>3.12.2.4. Imprint, Size of a Document, and Rep...</td>\n",
" <td>{'3.12.2.4': 'https://vault.tei-c.de/P5/3.0.0/...</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>9</th>\n",
+ " <th>10</th>\n",
" <td>series</td>\n",
" <td>(series information) contains information abou...</td>\n",
" <td>3.12.2.1. Analytic, Monographic, and Series Le...</td>\n",
" <td>{'3.12.2.1': 'https://vault.tei-c.de/P5/3.0.0/...</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>10</th>\n",
+ " <th>11</th>\n",
" <td>span</td>\n",
" <td>associates an interpretative annotation direct...</td>\n",
" <td>18.3. Spans and Interpretations</td>\n",
" <td>{'18.3': 'https://vault.tei-c.de/P5/3.0.0/doc/...</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>11</th>\n",
+ " <th>12</th>\n",
" <td>title</td>\n",
" <td>(title) contains a title for any kind of work.</td>\n",
" <td>3.12.2.2. Titles, Authors, and Editors 2.2.1. ...</td>\n",
@@ -289,12 +298,12 @@
"</div>"
]
},
- "execution_count": 11,
+ "execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
- "execution_count": 11
+ "execution_count": 13
},
{
"metadata": {
diff --git a/convert-anystyle-data/schema/tei-tags-documentation.json b/convert-anystyle-data/schema/tei-tags-documentation.json
index a5e7a9b..96623d2 100644
--- a/convert-anystyle-data/schema/tei-tags-documentation.json
+++ b/convert-anystyle-data/schema/tei-tags-documentation.json
@@ -8,6 +8,14 @@
"2.2.1": "https:\/\/vault.tei-c.de\/P5\/3.0.0\/doc\/tei-p5-doc\/en\/html\/HD.html#HD21"
}
},
+ {
+ "name": "biblScope",
+ "description": "(scope of bibliographic reference) defines the scope of a bibliographic reference, for example as a list of page numbers, or a named subdivision of a larger work. ",
+ "documentation": "3.12.2.5. Scopes and Ranges in Bibliographic Citations",
+ "urls": {
+ "3.12.2.5": "https:\/\/vault.tei-c.de\/P5\/3.0.0\/doc\/tei-p5-doc\/en\/html\/CO.html#COBICOB"
+ }
+ },
{
"name": "citedRange",
"description": "(cited range) defines the range of cited content, often represented by pages or other units ",
--
GitLab