From e21e09bc0e5c2239e6080d041ea16391f71d8b50 Mon Sep 17 00:00:00 2001
From: Juanje Mendoza <juanjemd@gmail.com>
Date: Wed, 7 Jan 2026 15:24:12 +0100
Subject: [PATCH 1/4] test 862 with a little change in remove_comments

---
 src/somef/somef_cli.py             |  1 +
 src/somef/test/test_JSON_export.py | 50 +++++++++++++++---------------
 src/somef/utils/markdown_utils.py  |  4 ++-
 3 files changed, 29 insertions(+), 26 deletions(-)

diff --git a/src/somef/somef_cli.py b/src/somef/somef_cli.py
index c6bc02e1..4b3d54a4 100644
--- a/src/somef/somef_cli.py
+++ b/src/somef/somef_cli.py
@@ -156,6 +156,7 @@ def cli_get_data(threshold, ignore_classifiers, repo_url=None, doc_src=None, loc
                                                                                         repository_metadata)
             logging.info("--> create excerpts")                                                                           
             excerpts = create_excerpts.create_excerpts(string_list)
+            logging.info("--> extract text excerpts headers")  
             excerpts_headers = mardown_parser.extract_text_excerpts_header(readme_unfiltered_text)
             header_parents = mardown_parser.extract_headers_parents(readme_unfiltered_text)
             score_dict = supervised_classification.run_classifiers(excerpts, file_paths)
diff --git a/src/somef/test/test_JSON_export.py b/src/somef/test/test_JSON_export.py
index 7cc72e2d..edd9b7ae 100644
--- a/src/somef/test/test_JSON_export.py
+++ b/src/somef/test/test_JSON_export.py
@@ -407,36 +407,36 @@ def test_issue_830(self):
     #         except Exception as e:
     #             print(f"Failed to delete {cls.json_file}: {e}")  
 
-    # def test_issue_862(self):
-    #     """Checks if this repository does not gets stuck when labeling headers"""
-    #     somef_cli.run_cli(threshold=0.8,
-    #                         ignore_classifiers=False,
-    #                         repo_url=None,
-    #                         local_repo=test_data_repositories + "componentInstaller",
-    #                         doc_src=None,
-    #                         in_file=None,
-    #                         output=test_data_path + "test_issue_862.json",
-    #                         graph_out=None,
-    #                         graph_format="turtle",
-    #                         codemeta_out=None,
-    #                         pretty=True,
-    #                         missing=False,
-    #                         readme_only=False)
+    def test_issue_862(self):
+        """Checks if this repository does not gets stuck when labeling headers"""
+        somef_cli.run_cli(threshold=0.8,
+                            ignore_classifiers=False,
+                            repo_url=None,
+                            local_repo=test_data_repositories + "componentInstaller",
+                            doc_src=None,
+                            in_file=None,
+                            output=test_data_path + "test_issue_862.json",
+                            graph_out=None,
+                            graph_format="turtle",
+                            codemeta_out=None,
+                            pretty=True,
+                            missing=False,
+                            readme_only=False)
         
-    #     text_file = open(test_data_path + "test_issue_862.json", "r")
-    #     data = text_file.read()
-    #     text_file.close()
-    #     json_content = json.loads(data)
+        text_file = open(test_data_path + "test_issue_862.json", "r")
+        data = text_file.read()
+        text_file.close()
+        json_content = json.loads(data)
 
-    #     assert "description" in json_content, "Missing 'description' property"
+        assert "description" in json_content, "Missing 'description' property"
    
-    #     assert len(json_content["description"]) > 0, "Description list is empty"
+        assert len(json_content["description"]) > 0, "Description list is empty"
    
-    #     first_desc = json_content["description"][0]["result"] 
-    #     assert "value" in first_desc, "Missing 'value' in description result"
-    #     assert first_desc["value"], "Description 'value' is empty"  
+        first_desc = json_content["description"][0]["result"] 
+        assert "value" in first_desc, "Missing 'value' in description result"
+        assert first_desc["value"], "Description 'value' is empty"  
         
-    #     os.remove(test_data_path + "test_issue_862.json")
+        os.remove(test_data_path + "test_issue_862.json")
 
     def test_issue_859(self):
         """Checks whether a repository without content works fine. Must have just some results from the API."""
diff --git a/src/somef/utils/markdown_utils.py b/src/somef/utils/markdown_utils.py
index e898d7d5..0ce5479c 100644
--- a/src/somef/utils/markdown_utils.py
+++ b/src/somef/utils/markdown_utils.py
@@ -63,6 +63,8 @@ def remove_comments(html_text):
     -------
     Markdown with no HTML comments
     """
-    comment_pattern = r'<!--(.*?)-->'
+    # comment_pattern = r'<!--(.*?)-->'
+    comment_pattern = r'<!--[\s\S]*?--\s*>'
+
     html_without_comments = re.sub(comment_pattern, '', html_text, flags=re.DOTALL)
     return html_without_comments

From 4ddc048116042175bfe06d40cbd1dbc23d0915ea Mon Sep 17 00:00:00 2001
From: Juanje Mendoza <juanjemd@gmail.com>
Date: Wed, 7 Jan 2026 15:53:38 +0100
Subject: [PATCH 2/4] new regex in remove_comment

---
 src/somef/utils/markdown_utils.py | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/src/somef/utils/markdown_utils.py b/src/somef/utils/markdown_utils.py
index 0ce5479c..65449251 100644
--- a/src/somef/utils/markdown_utils.py
+++ b/src/somef/utils/markdown_utils.py
@@ -64,7 +64,9 @@ def remove_comments(html_text):
     Markdown with no HTML comments
     """
     # comment_pattern = r'<!--(.*?)-->'
-    comment_pattern = r'<!--[\s\S]*?--\s*>'
+    # comment_pattern = r'<!--[\s\S]*?--\s*>'
+    comment_pattern = r'<!--[\s\S]*?--.*?>'
 
-    html_without_comments = re.sub(comment_pattern, '', html_text, flags=re.DOTALL)
+    html_without_comments = re.sub(comment_pattern, '', html_text)
+    print(html_without_comments)
     return html_without_comments

From bb1fcf8a34a47430ca1fc5fdda52486ec02f1b8b Mon Sep 17 00:00:00 2001
From: Juanje Mendoza <juanjemd@gmail.com>
Date: Wed, 7 Jan 2026 16:28:21 +0100
Subject: [PATCH 3/4] try something in header_analysis

---
 src/somef/header_analysis.py | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/src/somef/header_analysis.py b/src/somef/header_analysis.py
index b97cf28b..a759e507 100644
--- a/src/somef/header_analysis.py
+++ b/src/somef/header_analysis.py
@@ -138,6 +138,11 @@ def extract_header_content(text: str) -> Tuple[pd.DataFrame, str | None]:
 
     content, none_header_content = mardown_parser.extract_content_per_header(text, headers)
     parents = mardown_parser.extract_headers_parents(text)
+
+    min_len = min(len(header_list), len(content)) 
+    header_list = header_list[:min_len] 
+    content = content[:min_len]
+    
     df = pd.DataFrame({
         'Header': header_list,
         'Content': content,

From c05fd5d7c6b125adc4c63f10ec145f93771ec6cc Mon Sep 17 00:00:00 2001
From: Juanje Mendoza <juanjemd@gmail.com>
Date: Wed, 7 Jan 2026 16:48:23 +0100
Subject: [PATCH 4/4] loggins in test before PR

---
 .github/workflows/action-test-before-PR.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/.github/workflows/action-test-before-PR.yml b/.github/workflows/action-test-before-PR.yml
index d2ca2786..acfc8680 100644
--- a/.github/workflows/action-test-before-PR.yml
+++ b/.github/workflows/action-test-before-PR.yml
@@ -31,4 +31,4 @@ jobs:
         run: poetry run somef configure -a
         
       - name: Run pytest
-        run: poetry run pytest -v src/somef/test
+        run: poetry run pytest -v -s src/somef/test