Marty/pubs-extract
1
0
Fork 0
Code Issues Pull requests Projects Releases 2 Packages Activity

Format file

Browse source
This commit is contained in:
Marty Oehme 2022-12-22 23:21:13 +01:00
parent 8f01b93de2
commit e3aacc4b15
Signed by: Marty
GPG key ID: 73BA40D5AFAF49C9
1 changed files with 17 additions and 7 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

24
extract/extract.py
View file

@ -40,9 +40,15 @@ class ExtractPlugin(PapersPlugin):
# or `:: {annotation} :: {page} ::` # or `:: {annotation} :: {page} ::`
# and so on # and so on
self.on_import = conf["plugins"].get("extract", {}).get("on_import", False) self.on_import = conf["plugins"].get("extract", {}).get("on_import", False)
self.minimum_similarity = float(conf["plugins"].get("extract", {}).get("minimum_similarity", 0.75)) self.minimum_similarity = float(
self.highlight_prefix = conf["plugins"].get("extract", {}).get("quote_prefix", "> ") conf["plugins"].get("extract", {}).get("minimum_similarity", 0.75)
self.note_prefix = conf["plugins"].get("extract", {}).get("note_prefix", "Note: ") )
self.highlight_prefix = (
conf["plugins"].get("extract", {}).get("quote_prefix", "> ")
)
self.note_prefix = (
conf["plugins"].get("extract", {}).get("note_prefix", "Note: ")
)
def update_parser(self, subparsers, conf): def update_parser(self, subparsers, conf):
"""Allow the usage of the pubs extract subcommand""" """Allow the usage of the pubs extract subcommand"""
@ -133,12 +139,16 @@ class ExtractPlugin(PapersPlugin):
with fitz.Document(filename) as doc: with fitz.Document(filename) as doc:
for page in doc: for page in doc:
for annot in page.annots(): for annot in page.annots():
content = self._retrieve_annotation_content(page, annot, self.highlight_prefix, self.note_prefix) content = self._retrieve_annotation_content(
page, annot, self.highlight_prefix, self.note_prefix
)
if content: if content:
annotations.append(f"[{(page.number or 0) + 1}] {content}") annotations.append(f"[{(page.number or 0) + 1}] {content}")
return annotations return annotations
def _retrieve_annotation_content(self, page, annotation, highlight_prefix = "> ", note_prefix = "Note: "): def _retrieve_annotation_content(
self, page, annotation, highlight_prefix="> ", note_prefix="Note: "
):
"""Gets the text content of an annotation. """Gets the text content of an annotation.
Returns the actual content of an annotation. Sometimes Returns the actual content of an annotation. Sometimes
@ -151,7 +161,7 @@ class ExtractPlugin(PapersPlugin):
written = page.get_textbox(annotation.rect).replace("\n", " ") written = page.get_textbox(annotation.rect).replace("\n", " ")
# highlight with selection in note # highlight with selection in note
if Levenshtein.ratio(content,written) > self.minimum_similarity: if Levenshtein.ratio(content, written) > self.minimum_similarity:
return f"{highlight_prefix}{content}" return f"{highlight_prefix}{content}"
# an independent note, not a highlight # an independent note, not a highlight
elif content and not written: elif content and not written:
@ -175,7 +185,7 @@ class ExtractPlugin(PapersPlugin):
if annotations: if annotations:
output += f"------ {paper.citekey} ------\n\n" output += f"------ {paper.citekey} ------\n\n"
for annot in annotations: for annot in annotations:
output += f'{annot}\n\n' output += f"{annot}\n\n"
output += "\n" output += "\n"
print(output) print(output)