Merge pull request #408 from hakonhagland/kw_refs

Script to extract keyword URIs

scripts/python/pyproject.toml

@@ -28,6 +28,7 @@ fodt-extract-xml-tag = "fodt.splitter:extract_xml_tag"
 fodt-fix-ignored-keywords = "fodt.fix_ignored:fix_ignored"
 fodt-fix-footer-style = "fodt.fix_footer_style:fix_footer_style"
 fodt-fix-letter-k-footer = "fodt.fix_letter_k_footer:fix_letter_k_footer"
+fodt-gen-kw-uri-map = "fodt.keyword_linker:gen_kw_uri_map"
 fodt-remove-bookmarks-from-master-styles = "fodt.remove_bookmarks:remove_bookmarks_from_master_styles"
 fodt-remove-chapters = "fodt.splitter:remove_chapters"
 fodt-remove-elements = "fodt.splitter:remove_elements"

scripts/python/src/fodt/add_keyword.py

@@ -13,7 +13,7 @@
 
 from fodt.constants import ClickOptions, Directories, FileExtensions, KeywordStatus, Regex
 from fodt.create_subdocument import CreateSubDocument3
-from fodt.helpers import Helpers
+from fodt import helpers
 from fodt.remove_subsections import RemoveSubSections
 from fodt.templates import Templates
 from fodt.xml_helpers import XMLHelper
@@ -241,8 +241,8 @@ def __init__(
         status: KeywordStatus,
         appendix: bool
     ) -> None:
-        self.maindir = Helpers.get_maindir(maindir)
-        self.keyword_dir = Helpers.get_keyword_dir(keyword_dir, self.maindir)
+        self.maindir = helpers.get_maindir(maindir)
+        self.keyword_dir = helpers.get_keyword_dir(keyword_dir)
         self.keyword = keyword
         self.chapter = chapter
         self.section = section
@@ -259,16 +259,16 @@ def __init__(
 
     def add_keyword(self) -> None:
         self.documentdir = Path(self.maindir) / Directories.chapters
-        keyw_list = Helpers.read_keyword_order_v2(self.keyword_dir, self.chapter, self.section)
-        #keyw_list = Helpers.read_keyword_order(self.documentdir, self.chapter, self.section)
+        keyw_list = helpers.read_keyword_order_v2(self.keyword_dir, self.chapter, self.section)
+        #keyw_list = helpers.read_keyword_order(self.documentdir, self.chapter, self.section)
         keywords = set(keyw_list)
         if self.keyword in keywords:
             logging.info(f"Keyword {self.keyword} already exists. Aborting.")
             return
         keywords.add(self.keyword)
         keyw_list = sorted(list(keywords))
-        #Helpers.write_keyword_order(self.documentdir, self.chapter, self.section, keyw_list)
-        Helpers.write_keyword_order_v2(self.keyword_dir, self.chapter, self.section, keyw_list)
+        #helpers.write_keyword_order(self.documentdir, self.chapter, self.section, keyw_list)
+        helpers.write_keyword_order_v2(self.keyword_dir, self.chapter, self.section, keyw_list)
         logging.info(f"Added keyword {self.keyword} to chapter {self.chapter}, section {self.section}.")
         return
 
@@ -296,9 +296,9 @@ def update_appendixA(self) -> None:
     def update_chapter_document(self) -> None:
         logging.info(f"Updating chapter document {self.chapter}.")
         filename = self.documentdir / f"{self.chapter}.{FileExtensions.fodt}"
-        source_file = Helpers.create_backup_document(filename)
+        source_file = helpers.create_backup_document(filename)
         dest_file = filename
-        replace_callback = Helpers.replace_section_callback
+        replace_callback = helpers.replace_section_callback
         # NOTE: This will remove the subsection the first time it is called, and then
         #     if it is called again (for example using add-keyword), it will remove
         #     the inserted <text:section> tag that was inserted by the first call.
@@ -369,12 +369,12 @@ def add_keyword(
     appendix: bool
 ) -> None:
     logging.basicConfig(level=logging.INFO)
-    (chapter, section) = Helpers.split_section(section)
+    (chapter, section) = helpers.split_section(section)
     try:
         status = KeywordStatus[status.upper()]
     except ValueError:
         raise ValueError(f"Invalid status value: {status}.")
     add_keyword = AddKeyword(maindir, keyword_dir, keyword, chapter, section, title, status, appendix)
 
 if __name__ == "__main__":
-    add_keyword()
+    add_keyword()

scripts/python/src/fodt/constants.py

@@ -53,6 +53,7 @@ class FileExtensions():
 
 class FileNames():
     keywords = "keywords.txt"
+    kw_uri_map = "kw_uri_map.txt"
     main_document = "main.fodt"
     master_styles_fn = "master-styles.xml"
     office_attr_fn = "office_attrs.txt"

scripts/python/src/fodt/create_subdocument.py

@@ -6,7 +6,7 @@
 from fodt.automatic_styles_filter import AutomaticStylesFilter2, AutomaticStylesFilter3
 from fodt.constants import Directories, FileExtensions, FileNames, MetaSections
 from fodt.exceptions import InputException
-from fodt.helpers import Helpers
+from fodt import helpers
 from fodt.xml_helpers import XMLHelper
 from fodt.styles_filter import StylesFilter
 
@@ -36,7 +36,7 @@ def create_documents(self, parts: list[str], bookmark_info: list[str]|None = Non
             logging.info(f"Created FODT subdocument {outputfile}")
 
     def create_subsection_template(self, part: str, part_extra: str|None) -> str:
-        template = Helpers.read_keyword_template()
+        template = helpers.read_keyword_template()
         part_bookmark = f"{part}_{part_extra}" if part_extra is not None else part
         template = re.sub(r"###KEYWORD_NAME_BOOKMARK###", part_bookmark, template)
         template = re.sub(r"###KEYWORD_NAME###", part, template)
@@ -165,8 +165,8 @@ def __init__(self, maindir: str, chapter: str, section: str) -> None:
         self.outputdir = self.documentdir / Directories.subsections
         self.is_chapter = False
         parts = self.get_parts()
-        keyw_list = Helpers.read_keyword_order(self.documentdir, chapter, section)
-        self.keywords = Helpers.keywords_inverse_map(keyw_list)
+        keyw_list = helpers.read_keyword_order(self.documentdir, chapter, section)
+        self.keywords = helpers.keywords_inverse_map(keyw_list)
         self.add_keyword = False
         self.create_documents(parts)
 
@@ -202,7 +202,7 @@ def __init__(
         self.is_chapter = False
         parts = [self.keyword]
         parts_extra = [f"{self.chapter}_{self.section}"]
-        keyw_list = Helpers.read_keyword_order_v2(self.keyword_dir, chapter, section)
-        self.keywords = Helpers.keywords_inverse_map(keyw_list)
+        keyw_list = helpers.read_keyword_order_v2(self.keyword_dir, chapter, section)
+        self.keywords = helpers.keywords_inverse_map(keyw_list)
         self.add_keyword = True
         self.create_documents(parts, parts_extra)

scripts/python/src/fodt/extract_section.py

@@ -13,7 +13,7 @@
 )
 from fodt.automatic_styles_filter import AutomaticStylesFilter4
 from fodt.exceptions import ParsingException
-from fodt.helpers import Helpers
+from fodt import helpers
 from fodt.styles_filter import StylesFilter
 from fodt.xml_helpers import XMLHelper
 
@@ -200,7 +200,7 @@ def extract(self) -> tuple[str, str, set[str]]:
         parser = xml.sax.make_parser()
         handler = ExtractAndRemoveHandler(self.chapter, self.section)
         parser.setContentHandler(handler)
-        fn = Helpers.chapter_fodt_file_path(self.maindir, self.chapter)
+        fn = helpers.chapter_fodt_file_path(self.maindir, self.chapter)
         parser.parse(fn)
         return (handler.get_section(), handler.get_doc(), handler.get_styles())
 
@@ -228,7 +228,7 @@ def extract(self) -> str:
         self.create_section_file(section_txt, styles)
 
     def write_updated_chapter(self, doc: str) -> None:
-        fn = Helpers.chapter_fodt_file_path(self.maindir, self.chapter)
+        fn = helpers.chapter_fodt_file_path(self.maindir, self.chapter)
         with open(fn, "w", encoding='utf8') as f:
             f.write(doc)
         logging.info(f"Wrote updated chapter file to {fn}.")
@@ -250,10 +250,10 @@ def write_updated_chapter(self, doc: str) -> None:
 def extract_section(maindir: str, section: str) -> None:
     """Extract the appendix from a FODT file."""
     logging.basicConfig(level=logging.INFO)
-    (chapter, section) = Helpers.split_section(section)
+    (chapter, section) = helpers.split_section(section)
     logging.info(f"Extracting section {section} from chapter {chapter}.")
     extractor = ExtractSection(maindir, chapter, section)
     extractor.extract()
 
 if '__name__' == '__main__':
-    extract_section()
+    extract_section()

scripts/python/src/fodt/extract_subsections.py

@@ -10,7 +10,7 @@
 
 from fodt.constants import AutomaticStyles, Directories, FileNames, FileExtensions
 from fodt.exceptions import HandlerDoneException, InputException, ParsingException
-from fodt.helpers import Helpers
+from fodt import helpers
 from fodt.xml_helpers import XMLHelper
 
 class PartsHandler(xml.sax.handler.ContentHandler):
@@ -179,10 +179,10 @@ def __init__(
         section: int,
     ) -> None:
         parser = xml.sax.make_parser()
-        keyword_file = Helpers.keyword_file(outputdir, chapter, section)
+        keyword_file = helpers.keyword_file(outputdir, chapter, section)
         predefined_keywords = None
         if keyword_file.exists():
-            predefined_keywords = Helpers.read_keyword_order(outputdir, chapter, section)
+            predefined_keywords = helpers.read_keyword_order(outputdir, chapter, section)
         handler = PartsHandler(outputdir, chapter, section, predefined_keywords)
         parser.setContentHandler(handler)
         try: