Fix parsing table cells

CHANGELOG.md

@@ -1,13 +1,14 @@
-## 0.16.19-dev2
+## 0.16.19-dev3
 
 ### Enhancements
 
 ### Features
 
 ### Fixes
-- **fix a bug where table extraction is skipped when it shouldn't**. Pages with just one table as its content or starts with a table misses table extraction. The routing logic is now fixed.
+- **Fix a bug where table extraction is skipped when it shouldn't**. Pages with just one table as its content or starts with a table misses table extraction. The routing logic is now fixed.
 - **Correct deprecated `ruff` invocation in `make tidy`**.  This will future-proof it or avoid surprises if someone happens to upgrade Ruff.
 - **Remove upper bound constraint on python version** in setup.py. Python3.13 is not yet officially supported, but allow users to try.
+- **Fixes removing HTML elements from the inside of table cells** in html partition v=2.0. The HTML partitioner now correctly preserves HTML elements from the inside of table cells.
 
 ## 0.16.17
 

test_unstructured/documents/unstructured_json_output/example.json

@@ -4,6 +4,10 @@
         "metadata": {
             "category_depth": 0,
             "filename": "example.pdf",
+            "filetype": "text/html",
+            "languages": [
+                "eng"
+            ],
             "page_number": 1,
             "parent_id": "897a8a47377c4ad6aab839a929879537",
             "text_as_html": "<div class=\"Page\" data-page-number=\"1\" id=\"3a6b156a81764e17be128264241f8136\" />"
@@ -16,6 +20,10 @@
         "metadata": {
             "category_depth": 1,
             "filename": "example.pdf",
+            "filetype": "text/html",
+            "languages": [
+                "eng"
+            ],
             "page_number": 1,
             "parent_id": "3a6b156a81764e17be128264241f8136",
             "text_as_html": "<header class=\"Header\" id=\"45b3d0053468484ba1c7b53998115412\" />"
@@ -28,9 +36,13 @@
         "metadata": {
             "category_depth": 2,
             "filename": "example.pdf",
+            "filetype": "text/html",
+            "languages": [
+                "eng"
+            ],
             "page_number": 1,
             "parent_id": "45b3d0053468484ba1c7b53998115412",
-            "text_as_html": "<h1 class=\"Title\" id=\"c95473e8a3704fc2b418697f9fddb27b\">Header </h1>"
+            "text_as_html": "<h1 class=\"Title\" id=\"c95473e8a3704fc2b418697f9fddb27b\">Header</h1>"
         },
         "text": "Header",
         "type": "Title"
@@ -40,9 +52,13 @@
         "metadata": {
             "category_depth": 2,
             "filename": "example.pdf",
+            "filetype": "text/html",
+            "languages": [
+                "eng"
+            ],
             "page_number": 1,
             "parent_id": "45b3d0053468484ba1c7b53998115412",
-            "text_as_html": "<time class=\"CalendarDate\" id=\"379cbfdc16d44bd6a59e6cfabe6438d5\">Date: October 30, 2023 </time>"
+            "text_as_html": "<time class=\"CalendarDate\" id=\"379cbfdc16d44bd6a59e6cfabe6438d5\">Date: October 30, 2023</time>"
         },
         "text": "Date: October 30, 2023",
         "type": "UncategorizedText"
@@ -52,9 +68,13 @@
         "metadata": {
             "category_depth": 1,
             "filename": "example.pdf",
+            "filetype": "text/html",
+            "languages": [
+                "eng"
+            ],
             "page_number": 1,
             "parent_id": "3a6b156a81764e17be128264241f8136",
-            "text_as_html": "<form class=\"Form\" id=\"637c2f6935fb4353a5f73025ce04619d\"> <label class=\"FormField\" for=\"company-name\" id=\"50027cccbe1948c9853ce0de37b635c2\">From field name </label><input class=\"FormFieldValue\" id=\"0032242af75c4b37984ea7fea9aac74c\" value=\"Example value\" /></form>"
+            "text_as_html": "<form class=\"Form\" id=\"637c2f6935fb4353a5f73025ce04619d\"><label class=\"FormField\" for=\"company-name\" id=\"50027cccbe1948c9853ce0de37b635c2\">From field name</label><input class=\"FormFieldValue\" id=\"0032242af75c4b37984ea7fea9aac74c\" value=\"Example value\" /></form>"
         },
         "text": "From field name Example value",
         "type": "UncategorizedText"
@@ -64,6 +84,10 @@
         "metadata": {
             "category_depth": 1,
             "filename": "example.pdf",
+            "filetype": "text/html",
+            "languages": [
+                "eng"
+            ],
             "page_number": 1,
             "parent_id": "3a6b156a81764e17be128264241f8136",
             "text_as_html": "<section class=\"Section\" id=\"592422373ed741b68a077e2003f8ed81\" />"
@@ -76,9 +100,13 @@
         "metadata": {
             "category_depth": 2,
             "filename": "example.pdf",
+            "filetype": "text/html",
+            "languages": [
+                "eng"
+            ],
             "page_number": 1,
             "parent_id": "592422373ed741b68a077e2003f8ed81",
-            "text_as_html": "<table class=\"Table\" id=\"dc3792d4422e444f90876b56d0cfb20d\"> <thead> <tr> <th>Description</th><th>Row header</th></tr></thead><tbody> <tr> <td>Value description</td><td>50 $ (1.32 %)</td></tr></tbody></table>"
+            "text_as_html": "<table class=\"Table\" id=\"dc3792d4422e444f90876b56d0cfb20d\"><thead><tr><th>Description</th><th>Row header</th></tr></thead><tbody><tr><td>Value description</td><td><span>50 $</span><span>(1.32 %)</span></td></tr></tbody></table>"
         },
         "text": "Description Row header Value description 50 $ (1.32 %)",
         "type": "Table"
@@ -88,6 +116,10 @@
         "metadata": {
             "category_depth": 1,
             "filename": "example.pdf",
+            "filetype": "text/html",
+            "languages": [
+                "eng"
+            ],
             "page_number": 1,
             "parent_id": "3a6b156a81764e17be128264241f8136",
             "text_as_html": "<section class=\"Section\" id=\"1032242af75c4b37984ea7fea9aac74c\" />"
@@ -100,9 +132,13 @@
         "metadata": {
             "category_depth": 2,
             "filename": "example.pdf",
+            "filetype": "text/html",
+            "languages": [
+                "eng"
+            ],
             "page_number": 1,
             "parent_id": "1032242af75c4b37984ea7fea9aac74c",
-            "text_as_html": "<h2 class=\"Subtitle\" id=\"2a4e2c4a689f4f9a8c180b6b521e45c3\">2. Subtitle </h2>"
+            "text_as_html": "<h2 class=\"Subtitle\" id=\"2a4e2c4a689f4f9a8c180b6b521e45c3\">2. Subtitle</h2>"
         },
         "text": "2. Subtitle",
         "type": "Title"
@@ -112,9 +148,13 @@
         "metadata": {
             "category_depth": 2,
             "filename": "example.pdf",
+            "filetype": "text/html",
+            "languages": [
+                "eng"
+            ],
             "page_number": 1,
             "parent_id": "1032242af75c4b37984ea7fea9aac74c",
-            "text_as_html": "<p class=\"NarrativeText\" id=\"5591f7a4df01447e82515ce45f686fbe\">Paragraph text </p>"
+            "text_as_html": "<p class=\"NarrativeText\" id=\"5591f7a4df01447e82515ce45f686fbe\">Paragraph text</p>"
         },
         "text": "Paragraph text",
         "type": "NarrativeText"