Move away from remote fetching repositories

HTR-United · Jul 23, 2024 · fc70d1b · fc70d1b
1 parent 0410f57
commit fc70d1b
Show file tree

Hide file tree

Showing 29 changed files with 5,091 additions and 1 deletion.
diff --git a/.github/workflows/Catalog.yaml b/.github/workflows/Catalog.yaml
@@ -26,7 +26,7 @@ jobs:
         pip install htruc
     - name: Run HTRUC
       run: |
-        htruc make ./catalog --access_token ${{ secrets. GITHUB_TOKEN }} --graph-csv data.csv --statistics statistics.csv --output htr-united.yml --graph graph.png --json catalog.json --ids catalog-ids.json --organization htr-united --organization gallicorpora --remote --check-link --organization htromance-project
+        htruc make ./catalog --access_token ${{ secrets. GITHUB_TOKEN }} --graph-csv data.csv --statistics statistics.csv --output htr-united.yml --graph graph.png --json catalog.json --ids catalog-ids.json --check-link
     - name: Commit files
       run: |
         git config --local user.email "41898282+github-actions[bot]@users.noreply.github.com"

diff --git a/catalog-ids.json b/catalog-ids.json
@@ -0,0 +1 @@
+{"https://doi.org/10.5281/zenodo.5153263": "repo-00000", "https://zenodo.org/record/4780947#.YhN5pVvMLUQ": "repo-00001", "https://github.com/calfa-co/rasam-dataset": "repo-00002", "https://github.com/DesenrollandoElCordel/FoNDUE-Spanish-chapbooks-Dataset": "repo-00003", "https://zenodo.org/record/3333627#.YhN1G1vMLUQ": "repo-00004", "https://github.com/rescribe/carolineminuscule-groundtruth": "repo-00005", "http://dx.doi.org/10.34847/nkl.acb724xs": "repo-00006", "https://github.com/e-ditiones/OCR17plus": "repo-00007", "https://github.com/PSL-Chartes-HTR-Students/TNAH-2021-Projet-Notre-Dame": "repo-00008", "https://github.com/PSL-Chartes-HTR-Students/TNAH-2021-ArgusDesBrevets": "repo-00009", "https://github.com/PSL-Chartes-HTR-Students/TNAH-2021-DecameronFR": "repo-00010", "https://github.com/PSL-Chartes-HTR-Students/HN2021-Kovalewsky-1893": "repo-00011", "https://github.com/PSL-Chartes-HTR-Students/HN2021-ChateauChavigny": "repo-00012", "https://github.com/PSL-Chartes-HTR-Students/HN2021-Boccace": "repo-00013", "https://github.com/PSL-Chartes-HTR-Students/HN2021-Memorials_Jane_Lathrop_Stanford": "repo-00014", "https://github.com/PSL-Chartes-HTR-Students/TNAH-2021-Expositions_Universelles": "repo-00015", "https://github.com/PSL-Chartes-HTR-Students/TNAH-2021-Projet-Correspondance-Berlioz": "repo-00016", "https://github.com/jpmjpmjpm/genauto-td-htr.git": "repo-00017", "https://doi.org/10.5281/zenodo.5179361": "repo-00018", "HTR-United/tapuscorpus": "repo-00019", "HTR-United/timeuscorpus": "repo-00020", "HTR-United/dahncorpus": "repo-00021", "HTR-United/cremma-medieval": "repo-00022", "HTR-United/cremma-16-17-print": "repo-00023", "HTR-United/CREMMA-Medieval-LAT": "repo-00024", "HTR-United/CREMMA-MSS-17": "repo-00025", "HTR-United/CREMMA-MSS-18": "repo-00026", "HTR-United/CREMMA-MSS-19": "repo-00027", "HTR-United/CREMMA-MSS-20": "repo-00028", "HTR-United/lectaurep-bronod": "repo-00029", "HTR-United/lectaurep-mariages-et-divorces": "repo-00030", "HTR-United/lectaurep-repertoires": "repo-00031", "HTR-United/CREMMA-AN-TestamentDePoilus": "repo-00032", "HTR-United/cremma-wikipedia": "repo-00033", "Gallicorpora/HTR-MSS-15e-Siecle": "repo-00034", "Gallicorpora/HTR-incunable-15e-siecle": "repo-00035", "Gallicorpora/HTR-imprime-16e-siecle": "repo-00036", "Gallicorpora/HTR-imprime-17e-siecle": "repo-00037", "Gallicorpora/HTR-imprime-gothique-16e-siecle": "repo-00038", "Gallicorpora/HTR-imprime-18e-siecle": "repo-00039", "FoNDUE-HTR/FONDUE-FR-PRINT-17": "repo-00040", "FoNDUE-HTR/FONDUE-FR-PRINT-16": "repo-00041"}
diff --git a/catalog/almanach/dahn.yml b/catalog/almanach/dahn.yml
@@ -0,0 +1,134 @@
+authors:
+- name: Chiffoleau
+  roles:
+  - project-manager
+  - aligner
+  surname: Floriane
+characters:
+  members:
+  - e
+  - s
+  - a
+  - n
+  - r
+  - i
+  - t
+  - u
+  - o
+  - l
+  - d
+  - c
+  - m
+  - p
+  - ́
+  - ','
+  - v
+  - .
+  - f
+  - q
+  - g
+  - ̀
+  - '-'
+  - E
+  - b
+  - ’
+  - "'"
+  - h
+  - A
+  - L
+  - N
+  - x
+  - j
+  - S
+  - R
+  - I
+  - T
+  - M
+  - ̂
+  - C
+  - P
+  - y
+  - O
+  - ;
+  - '1'
+  - £
+  - U
+  - D
+  - B
+  - F
+  - J
+  - G
+  - '"'
+  - '0'
+  - z
+  - V
+  - '9'
+  - '2'
+  - ':'
+  - X
+  -  
+  - €
+  - H
+  - '5'
+  - '!'
+  - '3'
+  - '4'
+  - ̧
+  - °
+  - W
+  - Y
+  - '6'
+  - '8'
+  - '?'
+  - '7'
+  - K
+  - Q
+  - /
+  - (
+  - )
+  - k
+  - œ
+  - w
+  - ̈
+  - …
+  - Z
+  - –
+  - '&'
+  - '%'
+  - '='
+  - $
+  - _
+  mode: NFD
+description: OCR ground Truth dataset based on French 20th typewritten letters
+format: Alto-XML
+hands:
+  count: less-than-11
+  precision: exact
+language:
+- fra
+license:
+- name: CC-BY 4.0
+  url: https://creativecommons.org/licenses/by/4.0/
+production-software: eScriptorium + Kraken
+project-name: DAHN
+project-website: https://digitalintellectuals.hypotheses.org/category/dahn
+schema: https://htr-united.github.io/schema/2022-04-15/schema.json
+script:
+- iso: Latn
+script-type: only-typed
+time:
+  notAfter: '1924'
+  notBefore: '1914'
+title: DAHN Corpus
+url: https://github.com/HTR-United/dahncorpus
+volume:
+- count: 475849
+  metric: characters
+- count: 547
+  metric: files
+- count: 12539
+  metric: lines
+- count: 527
+  metric: pages
+- count: 547
+  metric: regions
diff --git a/catalog/almanach/lectaurep-bronod.yml b/catalog/almanach/lectaurep-bronod.yml
@@ -0,0 +1,103 @@
+authors:
+- name: Limon-Bonnet
+  roles:
+  - transcriber
+  - aligner
+  - quality-control
+  surname: Françoise
+- name: Chagué
+  roles:
+  - support
+  - project-manager
+  - quality-control
+  surname: Alix
+- name: Rostaing
+  roles:
+  - project-manager
+  surname: Aurélia
+characters:
+  members:
+  - e
+  - t
+  - a
+  - /
+  - '0'
+  - c
+  - n
+  - r
+  - m
+  - h
+  - p
+  - s
+  - o
+  - g
+  - '5'
+  - '7'
+  - '1'
+  - E
+  - .
+  - i
+  - '-'
+  - '3'
+  - '9'
+  - '2'
+  - f
+  - d
+  - '8'
+  - <
+  - l
+  - '{'
+  - ':'
+  - P
+  - A
+  - G
+  - '}'
+  - U
+  - x
+  - '>'
+  - b
+  - '4'
+  - '6'
+  mode: NFD
+citation-file-link: https://raw.githubusercontent.com/HTR-United/lectaurep-bronod/master/CITATION.cff
+description: "Ground truth for Maître Bronod’s registers, notary in Paris during the\
+  \ 18th century.\n"
+format: Page-XML
+hands:
+  count: '1'
+  precision: exact
+language:
+- fra
+license:
+- name: CC-BY 4.0
+  url: https://creativecommons.org/licenses/by/4.0/
+production-software: eScriptorium + Kraken
+project-name: "LECTAUREP\n"
+project-website: https://lectaurep.hypotheses.org/
+schema: https://htr-united.github.io/schema/2022-04-15/schema.json
+script:
+- iso: Latn
+script-type: only-manuscript
+sources:
+- link: ''
+  reference: Limon-Bonnet, M. (2021). Lectaurep-Bronod, ground truth for Maitre Bronod\u0027s
+    documents (French XVIIIth century) (Version 1.0) [Computer software]. https://doi.org/10.5072/zenodo.977735
+time:
+  notAfter: '1745'
+  notBefore: '1742'
+title: Notaires de Paris - Bronod
+transcription-guidelines: "Transcription fidèle aux manuscrits : la casse et les abréviations\
+  \ sont respectées. Les portions de texte suscrites sont précédées d'un symbole `^`.\
+  \ Pas de traitement particulier des éventuels s longs.'\n"
+url: https://github.com/HTR-United/lectaurep-bronod
+volume:
+- count: 359094
+  metric: characters
+- count: 100
+  metric: files
+- count: 3702
+  metric: lines
+- count: 200
+  metric: pages
+- count: 296
+  metric: regions
diff --git a/catalog/almanach/lectaurep-mariages-divorces.yml b/catalog/almanach/lectaurep-mariages-divorces.yml
@@ -0,0 +1,111 @@
+authors:
+- name: Denis
+  roles:
+  - transcriber
+  - aligner
+  surname: Nathalie
+- name: Rostaing
+  roles:
+  - project-manager
+  - quality-control
+  - support
+  surname: Aurélia
+- name: Chagué
+  roles:
+  - project-manager
+  - quality-control
+  - support
+  surname: Alix
+characters:
+  members:
+  - e
+  - t
+  - /
+  - a
+  - c
+  - '0'
+  - n
+  - r
+  - m
+  - h
+  - p
+  - s
+  - o
+  - g
+  - '1'
+  - '7'
+  - '2'
+  - E
+  - .
+  - i
+  - '-'
+  - f
+  - '9'
+  - d
+  - '8'
+  - '5'
+  - <
+  - l
+  - '{'
+  - ':'
+  - P
+  - A
+  - G
+  - '}'
+  - U
+  - x
+  - '>'
+  - b
+  - '4'
+  - '6'
+  - '3'
+  mode: NFD
+citation-file-link: https://raw.githubusercontent.com/HTR-United/lectaurep-mariages-et-divorces/main/CITATION.cff
+description: "Ground truth for the Registres des Contrats de Mariages et des Séparations\
+  \ et Divorces in Paris. The documents are written in Franch during the 19th century,\
+  \ contain many names and addresses. The information is organized in tables spreading\
+  \ on two pages. The table’s headers and the preamble are printed.\n"
+format: Page-XML
+hands:
+  count: more-than-10
+  precision: estimated
+language:
+- fra
+license:
+- name: CC-BY 4.0
+  url: https://creativecommons.org/licenses/by/4.0/
+production-software: eScriptorium + Kraken
+project-name: "LECTAUREP\n"
+project-website: https://lectaurep.hypotheses.org/
+schema: https://htr-united.github.io/schema/2022-04-15/schema.json
+script:
+- iso: Latn
+script-type: mainly-manuscript
+sources:
+- link: ''
+  reference: 'Rostaing, A., Denis, N., & Chagué, A. (2021). Lectaurep-Mariages-et-Divorces:
+    ground truth for the Enregistrements des Contrats de Mariages et des Séparations
+    et Divorces in Paris (French 19th century)  (Version 1.0) [Computer software].
+    https://doi.org/10.5072/zenodo.977697'
+time:
+  notAfter: '1928'
+  notBefore: '1829'
+title: Notaires de Paris - Mariages et Divorces
+transcription-guidelines: "The transcription respects what is written (abbreviations\
+  \ are not developed, capitalization follows 19th century practices). Superscripted\
+  \ portions of text are signaled by `^` and many signatures are transcription with\
+  \ ¥. The lines containing printed text are associated with the type `printed` and\
+  \ the signatures are associated with the type `signature`. Thus they can both be\
+  \ removed from the dataset if necessary.'\n"
+url: https://github.com/HTR-United/lectaurep-mariages-et-divorces
+volume:
+- count: 1969488
+  metric: characters
+- count: 104
+  metric: files
+- count: 20304
+  metric: lines
+- count: 105
+  metric: pages
+- count: 324
+  metric: regions