Merge pull request #127 from impresso/bugfix-invalid-ci-metadata

Bugfix invalid ci metadata
impresso · May 1, 2024 · 213e304 · 213e304
2 parents 4514054 + d6eb3b0
commit 213e304
Show file tree

Hide file tree

Showing 83 changed files with 6,334 additions and 2,416 deletions.
diff --git a/.github/workflows/python-publish.yml b/.github/workflows/python-publish.yml
@@ -0,0 +1,43 @@
+# This workflow will upload a Python Package using Twine when a release is created
+# For more information see: https://docs.github.com/en/actions/automating-builds-and-tests/building-and-testing-python#publishing-to-package-registries
+name: Upload Python Package to Test Pypi
+
+on:
+  release:
+    types: [published]
+  workflow_dispatch:
+
+permissions:
+  contents: read
+
+jobs:
+  deploy:
+    runs-on: ubuntu-latest
+
+    environment:
+      name: testpypi
+      url: https://test.pypi.org/p/impresso-text-importer
+
+    # permissions:
+    #  id-token: write
+
+    steps:
+      - uses: actions/checkout@v4
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.11'
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install build
+      - name: Build package
+        run: python -m build
+      - name: Publish test package
+        uses: pypa/gh-action-pypi-publish@release/v1
+        # pypa/gh-action-pypi-publish@27b31702a0e7fc50959f5ad993c78deac1bdfc29
+
+        with:
+          repository-url: https://test.pypi.org/legacy/
+          user: __token__
+          password: ${{ secrets.TEST_PYPI_TOKEN }}
diff --git a/.readthedocs.yaml b/.readthedocs.yaml
@@ -12,7 +12,7 @@ build:
 
   tools:
 
-    python: "3.10"
+    python: "3.11"
 
     # You can also specify other tool versions:
 

diff --git a/README.md b/README.md
@@ -22,7 +22,7 @@ The second project 'impresso - Media Monitoring of the Past II. Beyond Borders:
 
 Aiming to develop and consolidate tools to process and explore large-scale collections of historical newspapers and radio archives, and to study the impact of this tooling on historical research practices, _Impresso II_ builds upon the first project – 'impresso - Media Monitoring of the Past' (grant number [CRSII5_173719](http://p3.snf.ch/project-173719), Sinergia program). More information at https://impresso-project.ch.
 
-Copyright (C) 2023  The *impresso* team (contributors to this program: Matteo Romanello, Maud Ehrmann, Alex Flückinger, Edoardo Tarek Hölzl, Pauline Conti).
+Copyright (C) 2024  The *impresso* team (contributors to this program: Matteo Romanello, Maud Ehrmann, Alex Flückinger, Edoardo Tarek Hölzl, Pauline Conti).
 
 This program is free software: you can redistribute it and/or modify it under the terms of the GNU Affero General Public License as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version.
 

diff --git a/docs/_build/doctrees/architecture.doctree b/docs/_build/doctrees/architecture.doctree
diff --git a/docs/_build/doctrees/custom_importer.doctree b/docs/_build/doctrees/custom_importer.doctree
diff --git a/docs/_build/doctrees/environment.pickle b/docs/_build/doctrees/environment.pickle
diff --git a/docs/_build/doctrees/importers.doctree b/docs/_build/doctrees/importers.doctree
diff --git a/docs/_build/doctrees/importers/bl.doctree b/docs/_build/doctrees/importers/bl.doctree
diff --git a/docs/_build/doctrees/importers/bnf-en.doctree b/docs/_build/doctrees/importers/bnf-en.doctree
diff --git a/docs/_build/doctrees/importers/bnf.doctree b/docs/_build/doctrees/importers/bnf.doctree
diff --git a/docs/_build/doctrees/importers/fedgaz.doctree b/docs/_build/doctrees/importers/fedgaz.doctree
diff --git a/docs/_build/doctrees/importers/lux.doctree b/docs/_build/doctrees/importers/lux.doctree
diff --git a/docs/_build/doctrees/importers/mets-alto.doctree b/docs/_build/doctrees/importers/mets-alto.doctree
diff --git a/docs/_build/doctrees/importers/olive.doctree b/docs/_build/doctrees/importers/olive.doctree
diff --git a/docs/_build/doctrees/importers/rero.doctree b/docs/_build/doctrees/importers/rero.doctree
diff --git a/docs/_build/doctrees/importers/swa.doctree b/docs/_build/doctrees/importers/swa.doctree
diff --git a/docs/_build/doctrees/importers/tetml.doctree b/docs/_build/doctrees/importers/tetml.doctree
diff --git a/docs/_build/doctrees/index.doctree b/docs/_build/doctrees/index.doctree
diff --git a/docs/_build/doctrees/install.doctree b/docs/_build/doctrees/install.doctree
diff --git a/docs/_build/html/.buildinfo b/docs/_build/html/.buildinfo
@@ -1,4 +1,4 @@
 # Sphinx build info version 1
 # This file hashes the configuration used when building these files. When it is not found, a full rebuild will be done.
-config: 9ad8a57449e2e2c2f5e8c5e29b5f34c3
+config: 33afe7885988d347fbefaf2f285c0ba5
 tags: 645f666f9bcd5a90fca523b33c5a78b7
diff --git a/docs/_build/html/architecture.html b/docs/_build/html/architecture.html
diff --git a/docs/_build/html/custom_importer.html b/docs/_build/html/custom_importer.html
@@ -1,14 +1,12 @@
 <!DOCTYPE html>
-<html class="writer-html5" lang="en" data-content_root="./">
+<html class="writer-html5" lang="en" >
 <head>
-  <meta charset="utf-8" /><meta name="viewport" content="width=device-width, initial-scale=1" />
+  <meta charset="utf-8" /><meta name="generator" content="Docutils 0.18.1: http://docutils.sourceforge.net/" />
 
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
   <title>Writing a new importer &mdash; Impresso TextImporter  documentation</title>
-      <link rel="stylesheet" type="text/css" href="_static/pygments.css?v=80d5e7a1" />
-      <link rel="stylesheet" type="text/css" href="_static/css/theme.css?v=19f00094" />
-
-
+      <link rel="stylesheet" href="_static/pygments.css" type="text/css" />
+      <link rel="stylesheet" href="_static/css/theme.css" type="text/css" />
   <!--[if lt IE 9]>
     <script src="_static/js/html5shiv.min.js"></script>
   <![endif]-->
@@ -404,7 +402,7 @@ <h2>Test<a class="headerlink" href="#test" title="Link to this heading"></a><
   <hr/>
 
   <div role="contentinfo">
-    <p>&#169; Copyright 2023, Impresso - Media Monitoring of the Past - EPFL-DHLAB, UZH-ICL, UNILU-C2DH, UNIL-History..</p>
+    <p>&#169; Copyright 2024, Impresso - Media Monitoring of the Past - EPFL-DHLAB, UZH-ICL, UNILU-C2DH, UNIL-History..</p>
   </div>
 
   Built with <a href="https://www.sphinx-doc.org/">Sphinx</a> using a

diff --git a/docs/_build/html/genindex.html b/docs/_build/html/genindex.html
@@ -1,13 +1,11 @@
 <!DOCTYPE html>
-<html class="writer-html5" lang="en" data-content_root="./">
+<html class="writer-html5" lang="en" >
 <head>
   <meta charset="utf-8" />
   <meta name="viewport" content="width=device-width, initial-scale=1.0" />
   <title>Index &mdash; Impresso TextImporter  documentation</title>
-      <link rel="stylesheet" type="text/css" href="_static/pygments.css?v=80d5e7a1" />
-      <link rel="stylesheet" type="text/css" href="_static/css/theme.css?v=19f00094" />
-
-
+      <link rel="stylesheet" href="_static/pygments.css" type="text/css" />
+      <link rel="stylesheet" href="_static/css/theme.css" type="text/css" />
   <!--[if lt IE 9]>
     <script src="_static/js/html5shiv.min.js"></script>
   <![endif]-->
@@ -131,6 +129,8 @@ <h2 id="A">A</h2>
       </ul></li>
   </ul></td>
   <td style="width: 33%; vertical-align: top;"><ul>
+      <li><a href="importers.html#text_importer.utils.add_property">add_property() (in module text_importer.utils)</a>
+</li>
       <li><a href="importers/olive.html#text_importer.importers.olive.classes.OliveNewspaperIssue.archive">archive (text_importer.importers.olive.classes.OliveNewspaperIssue attribute)</a>
 
       <ul>
@@ -341,6 +341,8 @@ <h2 id="E">E</h2>
       </ul></li>
   </ul></td>
   <td style="width: 33%; vertical-align: top;"><ul>
+      <li><a href="importers.html#text_importer.utils.empty_folder">empty_folder() (in module text_importer.utils)</a>
+</li>
       <li><a href="importers/lux.html#text_importer.importers.lux.helpers.encode_ark">encode_ark() (in module text_importer.importers.lux.helpers)</a>
 </li>
       <li><a href="importers/bl.html#text_importer.importers.bl.classes.BlNewspaperPage.encoding">encoding (text_importer.importers.bl.classes.BlNewspaperPage attribute)</a>
@@ -392,6 +394,8 @@ <h2 id="F">F</h2>
       <li><a href="importers/tetml.html#text_importer.importers.tetml.helpers.filter_special_symbols">filter_special_symbols() (in module text_importer.importers.tetml.helpers)</a>
 </li>
       <li><a href="importers/lux.html#text_importer.importers.lux.helpers.find_section_articles">find_section_articles() (in module text_importer.importers.lux.helpers)</a>
+</li>
+      <li><a href="importers/bnf-en.html#text_importer.importers.bnf_en.detect.fix_api_year_mismatch">fix_api_year_mismatch() (in module text_importer.importers.bnf_en.detect)</a>
 </li>
   </ul></td>
 </tr></table>
@@ -417,10 +421,10 @@ <h2 id="G">G</h2>
       </ul></li>
       <li><a href="importers/swa.html#text_importer.importers.swa.classes.SWANewspaperPage.get_iiif_image">get_iiif_image() (text_importer.importers.swa.classes.SWANewspaperPage method)</a>
 </li>
-  </ul></td>
-  <td style="width: 33%; vertical-align: top;"><ul>
       <li><a href="importers.html#text_importer.utils.get_issue_schema">get_issue_schema() (in module text_importer.utils)</a>
 </li>
+  </ul></td>
+  <td style="width: 33%; vertical-align: top;"><ul>
       <li><a href="importers/bnf-en.html#text_importer.importers.bnf_en.detect.get_issues_iiif_arks">get_issues_iiif_arks() (in module text_importer.importers.bnf_en.detect)</a>
 </li>
       <li><a href="importers/bnf.html#text_importer.importers.bnf.helpers.get_journal_name">get_journal_name() (in module text_importer.importers.bnf.helpers)</a>
@@ -434,6 +438,8 @@ <h2 id="G">G</h2>
       <li><a href="importers.html#text_importer.utils.get_pkg_resource">get_pkg_resource() (in module text_importer.utils)</a>
 </li>
       <li><a href="importers/tetml.html#text_importer.importers.tetml.helpers.get_placed_image">get_placed_image() (in module text_importer.importers.tetml.helpers)</a>
+</li>
+      <li><a href="importers.html#text_importer.utils.get_reading_order">get_reading_order() (in module text_importer.utils)</a>
 </li>
       <li><a href="importers/tetml.html#text_importer.importers.tetml.helpers.get_tif_shape">get_tif_shape() (in module text_importer.importers.tetml.helpers)</a>
 </li>
@@ -1224,9 +1230,15 @@ <h2 id="W">W</h2>
   <td style="width: 33%; vertical-align: top;"><ul>
       <li><a href="importers/tetml.html#text_importer.importers.tetml.helpers.word2json">word2json() (in module text_importer.importers.tetml.helpers)</a>
 </li>
+      <li><a href="architecture.html#text_importer.importers.core.write_error">write_error() (in module text_importer.importers.core)</a>
+
+      <ul>
+        <li><a href="importers.html#text_importer.utils.write_error">(in module text_importer.utils)</a>
+</li>
+      </ul></li>
   </ul></td>
   <td style="width: 33%; vertical-align: top;"><ul>
-      <li><a href="architecture.html#text_importer.importers.core.write_error">write_error() (in module text_importer.importers.core)</a>
+      <li><a href="importers.html#text_importer.utils.write_jsonlines_file">write_jsonlines_file() (in module text_importer.utils)</a>
 </li>
   </ul></td>
 </tr></table>
@@ -1256,7 +1268,7 @@ <h2 id="X">X</h2>
   <hr/>
 
   <div role="contentinfo">
-    <p>&#169; Copyright 2023, Impresso - Media Monitoring of the Past - EPFL-DHLAB, UZH-ICL, UNILU-C2DH, UNIL-History..</p>
+    <p>&#169; Copyright 2024, Impresso - Media Monitoring of the Past - EPFL-DHLAB, UZH-ICL, UNILU-C2DH, UNIL-History..</p>
   </div>
 
   Built with <a href="https://www.sphinx-doc.org/">Sphinx</a> using a