Merge pull request #34 from oreillymedia/TOOLSREQ-8242-version-bump-and-cleanup

Toolsreq 8242 version bump and cleanup

Author: delfanbaum

README.md

@@ -72,6 +72,17 @@ Options:
 
 ## Release Notes
 
+### 1.0.7
+
+Features:
+- Add support for formal code examples in Python and R via the "example" cell tag
+- Add support for glossaries
+- Add basic support for bibtex bibliographies
+
+Bug fixes:
+- Fix bug with top-level heading IDs causing xrefs to fail
+- Remove extraneous spacing in figure captions
+
 ### 1.0.6
 - Add support for sidebars as described in the [Jupyter Book documentation](https://jupyterbook.org/en/stable/content/layout.html#sidebars-within-content)
 

jupyter_book_to_htmlbook/code_processing.py

@@ -14,7 +14,7 @@ def process_code(chapter, skip_numbering=False):
 
     for div in highlight_divs:
         try:
-            parent_classes = str(div.parent["class"])
+            parent_classes = str(div.parent.get("class"))
 
             # apply `data-type` attribute
             pre_tag = div.pre
@@ -57,9 +57,6 @@ def process_code(chapter, skip_numbering=False):
         except TypeError:
             logging.warning(f"Unable to apply cell numbering to {div}")
 
-        except KeyError:
-            logging.warning(f"Unable to apply cell numbering to {div}")
-
     return chapter
 
 
@@ -75,14 +72,14 @@ def number_codeblock(pre_block, cell_number):
     # grandparent of highlight div contains in/out information
     grandparent = pre_block.parent.parent.parent
 
-    if "cell_input" in str(grandparent["class"]):
+    if "cell_input" in str(grandparent.get("class")):
         in_block = True
         cell_number += 1
         marker = f"In [{cell_number}]: "
     elif (
-            "cell_output" in grandparent["class"] and
+            "cell_output" in grandparent.get("class") and
             # ensure we're not in a hidden-input cell
-            "tag_hide-input" not in grandparent.parent["class"]
+            "tag_hide-input" not in grandparent.parent.get("class")
          ):
         in_block = False
         marker = f"Out[{cell_number}]: "
@@ -141,7 +138,7 @@ def process_code_examples(chapter):
             logging.warning(
                 "Missing first two line comments for uuid and title." +
                 f"Unable to apply example formatting to {example_cell}.")
-            return example_cell
+            return chapter
 
         # ensure comments are within the first three spans (since we
         # expect an empty span to start based on their highlighter)

jupyter_book_to_htmlbook/figure_processing.py

@@ -1,5 +1,5 @@
 from pathlib import Path
-from bs4 import NavigableString
+from bs4 import NavigableString  # type: ignore
 
 
 def process_figures(chapter, build_dir: Path):

jupyter_book_to_htmlbook/file_processing.py

@@ -225,11 +225,14 @@ def process_chapter(toc_element,
     """
 
     chapter, ch_name = process_chapter_soup(toc_element)
+    logging.info(f"Processing {ch_name}...")
 
     if not chapter:  # guard against malformed files
-        return
-
-    logging.info(f"Processing {ch_name}...")
+        logging.warning(f"Failed to process {toc_element}.")
+        raise RuntimeError(
+            f"Failed to process {toc_element}. Please check for error in " +
+            "your source file(s). Contact the Tools team for additional " +
+            "support.")
 
     # perform cleans and processing
     chapter = clean_chapter(chapter)
@@ -248,7 +251,7 @@ def process_chapter(toc_element,
     chapter = process_sidebars(chapter)
     chapter = process_subsections(chapter)
 
-    if chapter["data-type"] == "glossary":
+    if chapter.get("data-type") == "glossary":
         add_glossary_datatypes(chapter)
 
     chapter, ids = process_ids(chapter, book_ids)

jupyter_book_to_htmlbook/footnote_processing.py

@@ -10,22 +10,21 @@ def process_footnotes(chapter):
     # move the contents of the ref to the anchor point
     for ref in footnote_refs:
         try:
-            ref_id = ref['href'].split('#')[-1]
+            ref_id = ref.get('href').split('#')[-1]
             # double next_sibling b/c next sibling is a space
             ref_location = chapter.find(
                                         "dt", {"id": ref_id}
                                         ).next_sibling.next_sibling
             footnote_contents = ref_location.find('p').children
             ref.name = 'span'
             ref['data-type'] = 'footnote'
-            del(ref['href'])
-            del(ref['class'])
-            del(ref['id'])
+            del ref['href']
+            del ref['class']
+            del ref['id']
             ref.string = ''
             for child in footnote_contents:
                 ref.append(child)
-        except KeyError:
-            logging.warning(f'Error converting footnote "{ref}".')
+
         except AttributeError:
             logging.warning(f'Error converting footnote "{ref}".')
     # remove the list of footnote contents

jupyter_book_to_htmlbook/reference_processing.py

@@ -34,7 +34,7 @@ def process_interal_refs(chapter):
             parent.contents = ref
             # remove any id tags on the parent to avoid duplicates
             del parent['id']
-        elif ref['href'].find('htt') > -1:
+        elif ref.get('href').find('htt') > -1:
             logging.warning(f"External image reference: {ref['href']}")
         else:  # i.e., non reference xrefs
             ref['data-type'] = 'xref'

jupyter_book_to_htmlbook/text_processing.py

@@ -52,7 +52,7 @@ def move_span_ids_to_sections(chapter):
                 span.next_sibling.name in ["h1", "h2", "h3", "h4", "h5"]
            ):
             # add span id to section
-            span.parent['id'] = span['id']
+            span.parent['id'] = span.get('id')
             # remove the now unneeded span
             span.decompose()
     return chapter

jupyter_book_to_htmlbook/toc_processing.py

@@ -44,7 +44,7 @@ def get_book_toc(src_dir: Path) -> list:
             toc = load(f.read(), SafeLoader)
             # exit if we see some format other than jb-book
             try:
-                if toc["format"] != "jb-book":
+                if toc.get("format") != "jb-book":
                     message = ("Unsupported jupyter book format: " +
                                toc["format"] + ". The only supported" +
                                " format is 'jb-book'.")