format code

Author: MartinSchobben

src/eo_datascience/clean_nb.py

@@ -3,52 +3,55 @@
 from pathlib import Path
 import re
 
-def clean_up_frontmatter(dir = './notebooks', save=True):
+
+def clean_up_frontmatter(dir="./notebooks", save=True):
     # Define the path to the notebooks
     nb_paths = find_ipynb(dir)
 
     # Iterate over the notebooks
     for nb_path in nb_paths:
         # Load the notebook
         nb = nbformat.read(nb_path, as_version=4)
-        if nb.cells[0].source.startswith('---'):
-            #Load frontmatter
-            fm = nb.cells[0].source.split('\n')
+        if nb.cells[0].source.startswith("---"):
+            # Load frontmatter
+            fm = nb.cells[0].source.split("\n")
 
             # Extract the title and the subtitle and convert
             i = 1
             line = fm[i]
             new_text = []
             while not line.startswith("---"):
-                if line.startswith('title'):
+                if line.startswith("title"):
                     new_text.append(f"# {line.split(': ')[1]}")
-                if line.startswith('subtitle'):
+                if line.startswith("subtitle"):
                     new_text.append(f"**{line.split(': ')[1]}**")
 
                 i += 1
                 line = fm[i]
 
-            new_text += fm[i+1:]
+            new_text += fm[i + 1 :]
             nb.cells[0].source = "\n".join(new_text) + "\n"
         # Save notebook
         if save:
             nbformat.write(nb, nb_path)
         else:
             return nb
 
+
 def convert_bibliography(nb_path="./notebooks/references.ipynb", save=True):
     nb = nbformat.read(nb_path, as_version=4)
     nb.cells[0].source = """# References
 
 ```{bibliography}
 ```
 """
-     # Save the notebook
+    # Save the notebook
     if save:
         nbformat.write(nb, nb_path)
     else:
         return nb
 
+
 def convert_callout_notes(dir="./notebooks", save=True):
     nb_paths = find_ipynb(dir)
 
@@ -57,27 +60,32 @@ def convert_callout_notes(dir="./notebooks", save=True):
         # Load the notebook
         nb = nbformat.read(nb_path, as_version=4)
         for i in range(len(nb.cells)):
-
             if nb.cells[i]["cell_type"] == "markdown":
                 nb.cells[i].source = quarto_note_replace(nb.cells[i].source)
 
-     # Save the notebook
+    # Save the notebook
     if save:
         nbformat.write(nb, nb_path)
     else:
         return nb
-    
+
+
 def quarto_note_replace(quarto):
     note_rst_start = r":::{note}"
     note_rst_end = r":::"
     nts = re.findall(r"(?<=:::\s\{\.callout\-note\})[^:::]+", quarto)
     for i in nts:
-        quarto = re.sub(r":::\s\{\.callout\-note\}" + re.escape(i) + r":::", note_rst_start + i + note_rst_end, quarto)
+        quarto = re.sub(
+            r":::\s\{\.callout\-note\}" + re.escape(i) + r":::",
+            note_rst_start + i + note_rst_end,
+            quarto,
+        )
     return quarto
 
+
 def convert_refs(dir="./notebooks", save=True):
     nb_paths = find_ipynb(dir)
-    
+
     # Iterate over the notebooks
     for nb_path in nb_paths:
         # Load the notebook
@@ -95,35 +103,40 @@ def convert_refs(dir="./notebooks", save=True):
         else:
             return nb
 
+
 def quarto_ref_figure_replace(quarto):
     bibs = re.findall(r"(?<=\(\@)[^\)]+", quarto)
     for i in bibs:
         quarto = re.sub(r"\(\@" + i + "\)", r"", quarto)
     return quarto
 
+
 def quarto_ref_person_replace(quarto):
     bibs = re.findall(r"(?<=\[\@)[^\]]+", quarto)
     for i in bibs:
         quarto = re.sub(r"\[\@" + i + "\]", r"{cite:p}`" + i + "`", quarto)
     return quarto
 
+
 def quarto_ref_time_replace(quarto):
     bibs = re.findall(r"(?<=\@)[^\s]+", quarto)
     for i in bibs:
         quarto = re.sub(r"\@" + i, r"{cite:t}`" + i + "`", quarto)
     return quarto
 
+
 def find_ipynb(dir):
     root = Path(dir).resolve()
-    nb_paths = [root / file for file in os.listdir(root) if file.endswith('.ipynb')]
+    nb_paths = [root / file for file in os.listdir(root) if file.endswith(".ipynb")]
     return nb_paths
 
+
 def main():
     clean_up_frontmatter()
     convert_callout_notes()
     convert_refs()
     convert_bibliography()
 
 
-if __name__ == '__main__':
-    main()
+if __name__ == "__main__":
+    main()

tests/test_quarto_nb_conversions.py

@@ -1,20 +1,46 @@
 import nbformat
 from pathlib import Path
 import pytest
-from eo_datascience.clean_nb import clean_up_frontmatter, convert_refs, quarto_ref_person_replace, quarto_ref_time_replace, \
-    convert_callout_notes, quarto_note_replace
+from eo_datascience.clean_nb import (
+    clean_up_frontmatter,
+    convert_refs,
+    quarto_ref_person_replace,
+    quarto_ref_time_replace,
+    convert_callout_notes,
+    quarto_note_replace,
+    find_ipynb,
+)
+
 
 def test_remove_front_matter():
-    assert clean_up_frontmatter("./tests", False)["cells"][0]["source"] == '# This a mock Jupyter file\n**We use it for testing**\n\nSome other text, which should not be deleted!\n'
+    assert (
+        clean_up_frontmatter("./tests", False)["cells"][0]["source"]
+        == "# This a mock Jupyter file\n**We use it for testing**\n\nSome other text, which should not be deleted!\n"
+    )
+
+
+def test_find_ipynb():
+    assert find_ipynb("tests")[0].stem == "mock"
+
 
 def test_conversion_of_refs():
-    quarto = [r"lorem ipsum [@anon2024] and [@anon2025]", r"lorem ipsum @anon2024 and @anon2025"]
+    quarto = [
+        r"lorem ipsum [@anon2024] and [@anon2025]",
+        r"lorem ipsum @anon2024 and @anon2025",
+    ]
     quarto[0] = quarto_ref_person_replace(quarto[0])
     quarto[1] = quarto_ref_time_replace(quarto[1])
-    assert quarto == [r"lorem ipsum {cite:p}`anon2024` and {cite:p}`anon2025`", r"lorem ipsum {cite:t}`anon2024` and {cite:t}`anon2025`"]
-    assert convert_refs("./tests", False)["cells"][2]["source"] == r"lorem ipsum {cite:p}`anon2024` and {cite:p}`anon2025` and lorem ipsum {cite:t}`anon2024` and {cite:t}`anon2025`"
+    assert quarto == [
+        r"lorem ipsum {cite:p}`anon2024` and {cite:p}`anon2025`",
+        r"lorem ipsum {cite:t}`anon2024` and {cite:t}`anon2025`",
+    ]
+    assert (
+        convert_refs("./tests", False)["cells"][2]["source"]
+        == r"lorem ipsum {cite:p}`anon2024` and {cite:p}`anon2025` and lorem ipsum {cite:t}`anon2024` and {cite:t}`anon2025`"
+    )
+
 
 def test_conversion_of_callout_notes():
-    rst = ':::{note}\nThis a callout note.\n:::'
+    rst = ":::{note}\nThis a callout note.\n:::"
     assert quarto_note_replace(r"::: {.callout-note}\nThis a callout note.\n:::") == rst
-    assert convert_callout_notes("./tests", False)["cells"][1]["source"]  == rst
+    assert convert_callout_notes("./tests", False)["cells"][1]["source"] == rst