Merge pull request #15 from C2DH/dev

url issue fix

article-check-script/script.py

@@ -8,7 +8,7 @@
 
 def main_func(REPO_URL, PERSONAL_TOKEN, NEW_REPO_NAME):
 
-    f = open("../config.json")
+    f = open("./config.json")
 
     config_file = json.load(f)
 

preflight.py

@@ -9,6 +9,8 @@
 
 BASE_URL = "https://journalofdigitalhistory.org/en/notebook-viewer/"
 
+FIRST_PARAGRAPH = "Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum."
+
 
 def encode_notebook_url(url):
     # URL-encode the string
@@ -94,42 +96,39 @@ def generate_report(output, notebook, workspace="", action_outputs={}, contents=
     print(f"::debug::generatereport output:{output} notebook:{notebook}")
     output_filepath = os.path.join(workspace, output)
     count = len(contents["cells"])
-    # Open the file for writing and handle any errors
-    try:
-        with open(output_filepath, "w", encoding="utf-8") as output_file:
-            output_file.write(
-                f"# Report for {notebook} \u2764 \n\n"
-            )  # Write "#Hello" with a heart utf8 character
-            # count cells of each type. check for empty cells
-            cell_types = {"code_empty": 0}
-            for cell in contents["cells"]:
-                cell_type = cell["cell_type"]
-                if cell_type not in cell_types:
-                    cell_types[cell_type] = 0
-                cell_types[cell_type] += 1
-                if cell_type == "code":
-                    if len(cell["source"]) == 0:
-                        cell_types["code_empty"] += 1
-            # write cell counts
-            config_file = open("config.json")
-
-            config_file_text = json.load(config_file)
-
-            config_file.close()
-            first_paragraph = str(config_file_text["first_paragraph"] + "\n\n")
-            output_file.write(first_paragraph)
-            output_file.write("## Cell Counts   \n")
-            output_file.write(f"**all cells: {count}**  \n")
-            for cell_type, count in cell_types.items():
-                output_file.write(f"{cell_type}: {count}   \n")
-            # write every action_output
-            output_file.write("\n## Action Outputs\n")
-            for key, value in action_outputs.items():
-                output_file.write(f"{value}\n")
-    except IOError:
-        # bad
-        print(f"::error::Bad things happened when open or write to {output}!")
-        sys.exit(1)
+
+    def write_result(count):
+        try:
+            with open(output_filepath, "w", encoding="utf-8") as output_file:
+                output_file.write(
+                    f"# Report for {notebook} \u2764 \n\n"
+                )  # Write "#Hello" with a heart utf8 character
+                # count cells of each type. check for empty cells
+                cell_types = {"code_empty": 0}
+                for cell in contents["cells"]:
+                    cell_type = cell["cell_type"]
+                    if cell_type not in cell_types:
+                        cell_types[cell_type] = 0
+                    cell_types[cell_type] += 1
+                    if cell_type == "code":
+                        if len(cell["source"]) == 0:
+                            cell_types["code_empty"] += 1
+                # write cell counts
+                output_file.write(FIRST_PARAGRAPH + "\n\n")
+                output_file.write("## Cell Counts   \n")
+                output_file.write(f"**all cells: {count}**  \n")
+                for cell_type, count in cell_types.items():
+                    output_file.write(f"{cell_type}: {count}   \n")
+                # write every action_output
+                output_file.write("\n## Action Outputs\n")
+                for key, value in action_outputs.items():
+                    output_file.write(f"{value}\n")
+            output_file.close()
+        except IOError:
+            # bad
+            write_result(count)
+
+    write_result(count)
 
 
 def main(

preflight_report.md

@@ -1,38 +1,95 @@
-# Report for example/article-altair.ipynb ❤ 
+# Report for example/article_urls_problem.ipynb ❤ 
 
 Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum.
 
 ## Cell Counts   
-**all cells: 147**  
+**all cells: 111**  
 code_empty: 0   
-markdown: 115   
-code: 32   
+markdown: 69   
+code: 42   
 
 ## Action Outputs
 
 ### Size
-**total cells: 147**
+**total cells: 111**
 
 ### Check URLs
 
 
-**Impossible to verify (non-404 error code - 4):**
+> [!CAUTION]
+> **Invalid URLs are present, please review the referenced URLs list.**
+
+**Invalid URLs (404 - 13):**
+
+
+> [!WARNING]
+> **Invalid URL (404):** https://github.com/hepplerj/whatisdigitalhumanities.
+
+> [!WARNING]
+> **Invalid URL (404):** https://weltliteratur.net/dh-tools-used-in-research/,
+
+> [!WARNING]
+> **Invalid URL (404):** https://doi.org/10.34666/k1de-j489,
+
+> [!WARNING]
+> **Invalid URL (404):** https://dh-abstracts.library.virginia.edu/downloads.
+
+> [!WARNING]
+> **Invalid URL (404):** https://github.com/Digital-Humanities-Quarterly/dhq-journal/tree/main/data/dhq-xml.
+
+> [!WARNING]
+> **Invalid URL (404):** https://github.com/ZoeLeBlanc/dhq_scraper.
+
+> [!WARNING]
+> **Invalid URL (404):** https://github.com/jrladd/network_navigator.
+
+> [!WARNING]
+> **Invalid URL (404):** https://networknavigator.jrladd.com/,
+
+> [!WARNING]
+> **Invalid URL (404):** https://getbootstrap.com/docs/4.0/about/history/>
+
+> [!WARNING]
+> **Invalid URL (404):** https://github.com/EvanLi/Github-Ranking/blob/master/Top100/Top-100-stars.md>.
+
+> [!WARNING]
+> **Invalid URL (404):** https://raw.githubusercontent.com/melaniewalsh/sample-social-network-datasets/master/sample-datasets/quakers/quaker-edges.csv"
+
+> [!WARNING]
+> **Invalid URL (404):** https://networkx.org/documentation/stable/developer/about_us.html,
+
+> [!WARNING]
+> **Invalid URL (404):** https://graphology.github.io/,
+
+**Impossible to verify (non-404 error code - 6):**
 
 Invalid URL (Other - 301): https://orcid.org/sites/default/files/images/orcid_16x16.png
-Invalid URL (Other - 301): https://worldcat.org/identities/lccn-n50070935/
-Invalid URL (Other - 301): https://worldcat.org/identities/lccn-n50055088/
-Invalid URL (Other - 301): https://worldcat.org/identities/lccn-no90018047/
+Invalid URL (Other - 403): https://www.canva.com/ai-image-generator/
+Invalid URL (Other - 301): http://tapor.ca/tools/category/Network%20Analysis.
+Invalid URL (Other - 302): https://dh-abstracts.library.cmu.edu.
+Invalid URL (Other - 503): https://web.archive.org/web/20080912001706/https://gephi.org/
+Invalid URL (Other - 302): https://github.com/jrladd/network_navigator/pull/7>.
 
 > [!TIP]
 > Even if some of the urls listed above don't seem to be broken, try to replace them with the valid ones as they might become unavailable soon.
 
 
-**Valid URLs (200 - 6):**
+**Valid URLs (200 - 16):**
 
-2. https://orcid.org/0000-0001-8618-6800
-3. https://orcid.org/0000-0002-6951-8014
-4. https://orcid.org/0000-0002-0301-2029
-5. https://licensebuttons.net/l/by/4.0/88x31.png
-6. https://creativecommons.org/licenses/by/4.0/
-7. https://github.com/jdh-observer/jdh002-VeaK58WBs82C
+2. https://orcid.org/0000-0002-5440-062X
+3. https://orcid.org/0000-0003-2012-8805
+4. https://licensebuttons.net/l/by-nc-nd/4.0/88x31.png
+5. https://creativecommons.org/licenses/by-nc-nd/4.0/
+13. https://digitalhumanities.org/dhq/
+18. https://github.com/gephi/gephi/commit/c1a1b8316427b1e5c6e0ea5ea8031a016b7ba2c1
+22. https://stackoverflow.com/questions/29288592/bootstrap-min-css-size-from-cdn-shows-a-surprising-size-in-devtools>.
+23. https://github.com/jrladd/network_navigator/issues/3>
+27. https://felix-kling.de/jsnetworkx/
+28. https://d3js.org
+29. https://www.khronos.org/api/webgl
+30. https://d3js.org/what-is-d3#d3-is-for-bespoke-visualization
+32. https://www.sigmajs.org/
+33. http://vis.stanford.edu/papers/d3
+34. https://medialab.sciencespo.fr/en/tools/
+35. https://github.com/melaniewalsh/sample-social-network-datasets
 

report.md

@@ -3,6 +3,7 @@
 Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum.
 
 ## Cell Counts   
+
 **all cells: 71**  
 code_empty: 1   
 markdown: 35   
@@ -11,21 +12,22 @@ code: 36
 ## Action Outputs
 
 ### Size
+
 **total cells: 71**
 ## Kernel Checks: 
 
 > [!CAUTION]
- > Error: Python versions don't match. The notebook is using **python-3.7.10**, when **python-3.11** is required.
+> Error: Python versions don't match. The notebook is using **python-3.7.10**, when **python-3.11** is required.
+
 
 > [!TIP]
- > Try changing **runtime.txt** to resolve the error above.
+> Try changing **runtime.txt** to resolve the error above.
 
 ### Citations Found with problem:
 
 
 ### Check HTML
 
-
 ### Check Output Sizes and Rules
 - Table found in output of cell 16
 > First words of input cell: df=pd.read_csv("https://raw.githubusercontent.com/mkrzmr/jdh/main/script/file_AA_sm.csv") df.drop('Unnamed: 0', axis=1, inplace=True)
@@ -46,7 +48,7 @@ Total number of audios: 4
 | Mimetype | Presence |
 | --- | --- |
 | text/html | True |
-| text/plain | False |
+| text/plain | True |
 | image/png | True |
 | audio | False |