added cluster_id filter (#7)

impresso · Oct 16, 2024 · f8b1cd9 · f8b1cd9
1 parent c9ef79d
commit f8b1cd9
Show file tree

Hide file tree

Showing 3 changed files with 149 additions and 0 deletions.
diff --git a/examples/notebooks/textReuse.ipynb b/examples/notebooks/textReuse.ipynb
@@ -2048,6 +2048,148 @@
     ")"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Find passages for a cluster by its ID"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<h2>FindTextReusePassages result</h2>\n",
+       "<div>Contains <b>2</b> items of <b>2</b> total items.</div>\n",
+       "<br/>\n",
+       "See this result in the <a href=\"https://impresso-project.ch/app/text-reuse/passages?sort=clusterSize&sq=CiEYHSoddHItbm9icC1hbGwtdjAxLWMxMzc0Mzg5NzgzMzI=&p=1\">Impresso App</a>.\n",
+       "<h3>Data preview:</h3>\n",
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>offsetStart</th>\n",
+       "      <th>offsetEnd</th>\n",
+       "      <th>content</th>\n",
+       "      <th>title</th>\n",
+       "      <th>pageNumbers</th>\n",
+       "      <th>collections</th>\n",
+       "      <th>connectedClusters</th>\n",
+       "      <th>isFront</th>\n",
+       "      <th>size</th>\n",
+       "      <th>date</th>\n",
+       "      <th>pageRegions</th>\n",
+       "      <th>article.id</th>\n",
+       "      <th>textReuseCluster.id</th>\n",
+       "      <th>textReuseCluster.clusterSize</th>\n",
+       "      <th>textReuseCluster.timeDifferenceDay</th>\n",
+       "      <th>textReuseCluster.lexicalOverlap</th>\n",
+       "      <th>newspaper.id</th>\n",
+       "      <th>issue.id</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>id</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>c137438978332-LLE-1891-07-21-a-i0023@3354:5682</th>\n",
+       "      <td>3354</td>\n",
+       "      <td>5682</td>\n",
+       "      <td>Un rapport géné-\\nral au roi Léopold sur la si...</td>\n",
+       "      <td>BULLETIN POLITIQUE</td>\n",
+       "      <td>[1]</td>\n",
+       "      <td>[local-duma-x9GD_Bj6, local-eb-ikYoMqvi]</td>\n",
+       "      <td>[{'id': 'tr-nobp-all-v01-c137438978332'}, {'id...</td>\n",
+       "      <td>True</td>\n",
+       "      <td>2328</td>\n",
+       "      <td>1891-07-21T00:00:00+00:00</td>\n",
+       "      <td>[657,609,1237,3220]</td>\n",
+       "      <td>LLE-1891-07-21-a-i0023</td>\n",
+       "      <td>tr-nobp-all-v01-c137438978332</td>\n",
+       "      <td>2</td>\n",
+       "      <td>1</td>\n",
+       "      <td>59.183673</td>\n",
+       "      <td>LLE</td>\n",
+       "      <td>LLE-1891-07-21-a</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>c137438978332-indeplux-1891-07-20-a-i0012@2514:5104</th>\n",
+       "      <td>2514</td>\n",
+       "      <td>5104</td>\n",
+       "      <td>Un rapport général au roi Léopold\\nsur la situ...</td>\n",
+       "      <td>Le Congo.</td>\n",
+       "      <td>[1]</td>\n",
+       "      <td>[]</td>\n",
+       "      <td>[{'id': 'tr-nobp-all-v01-c137438978332'}, {'id...</td>\n",
+       "      <td>True</td>\n",
+       "      <td>2590</td>\n",
+       "      <td>1891-07-20T00:00:00+00:00</td>\n",
+       "      <td>[1822,976,1565,3353]</td>\n",
+       "      <td>indeplux-1891-07-20-a-i0012</td>\n",
+       "      <td>tr-nobp-all-v01-c137438978332</td>\n",
+       "      <td>2</td>\n",
+       "      <td>1</td>\n",
+       "      <td>59.183673</td>\n",
+       "      <td>indeplux</td>\n",
+       "      <td>indeplux-1891-07-20-a</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "<impresso.resources.text_reuse.passages.FindTextReusePassagesContainer at 0x111a1d8d0>"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "impresso.text_reuse.passages.find(\n",
+    "    cluster_id=\"tr-nobp-all-v01-c137438978332\",\n",
+    "    order_by=\"clusterSize\",\n",
+    ")"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},

diff --git a/impresso/resources/text_reuse/clusters.py b/impresso/resources/text_reuse/clusters.py
@@ -254,6 +254,7 @@ def _build_cluster_facet_filters(
 
 def _build_filters(
     text: str | None = None,
+    cluster_id: str | AND[str] | OR[str] | None = None,
     cluster_size: Range | AND[Range] | OR[Range] | None = None,
     title: str | AND[str] | OR[str] | None = None,
     lexical_overlap: Range | AND[Range] | OR[Range] | None = None,
@@ -273,6 +274,8 @@ def _build_filters(
     filters: list[Filter] = []
     if text is not None:
         filters.extend(and_or_filter(text, "string"))
+    if cluster_id is not None:
+        filters.extend(and_or_filter(cluster_id, "text_reuse_cluster"))
     if cluster_size is not None:
         filters.extend(
             and_or_filter(

diff --git a/impresso/resources/text_reuse/passages.py b/impresso/resources/text_reuse/passages.py
@@ -54,6 +54,7 @@ def find(
         limit: int | None = None,
         offset: int | None = None,
         order_by: FindTextReusePassagesOrderByLiteral | None = None,
+        cluster_id: str | AND[str] | OR[str] | None = None,
         cluster_size: Range | AND[Range] | OR[Range] | None = None,
         title: str | AND[str] | OR[str] | None = None,
         lexical_overlap: Range | AND[Range] | OR[Range] | None = None,
@@ -70,6 +71,7 @@ def find(
     ) -> FindTextReusePassagesContainer:
         # reusing build filters from clusters - they are the same
         filters = _build_filters(
+            cluster_id=cluster_id,
             cluster_size=cluster_size,
             title=title,
             lexical_overlap=lexical_overlap,
@@ -119,6 +121,7 @@ def facet(
         limit: int | None = None,
         offset: int | None = None,
         order_by: FindTextReusePassagesOrderByLiteral | None = None,
+        cluster_id: str | AND[str] | OR[str] | None = None,
         cluster_size: Range | AND[Range] | OR[Range] | None = None,
         title: str | AND[str] | OR[str] | None = None,
         lexical_overlap: Range | AND[Range] | OR[Range] | None = None,
@@ -138,6 +141,7 @@ def facet(
             raise ValueError(f"{facet} is not a valid value")
 
         filters = _build_filters(
+            cluster_id=cluster_id,
             cluster_size=cluster_size,
             title=title,
             lexical_overlap=lexical_overlap,