Marty Oehme
765de505bb
The AnnotatedDocument class was, essentially, a simple tuple of a document and a list of annotations. While not bad in a vacuum, it is unwieldy and passing this around instead of a document, annotations, or both where necessary is more restrictive and frankly unnecessary. This commit removes the data class and any instances of its use. Instead, we now pass the individual components around to anything that needs them. This also frees us up to pass only annotations around for example. We also do not iterate through the selected papis documents to work on in each exporter anymore (since we only pass a single document), but in the main function itself. This leads to less duplication and makes the overall run function the overall single source of iteration through selected documents. Everything else only knows about a single document - the one it is operating on - which seems much neater. For now, it does not change much, but should make later work on extra exporters or extractors easier.
75 lines
1.8 KiB
Python
75 lines
1.8 KiB
Python
from papis.document import Document
|
|
from papis_extract.annotation import Annotation
|
|
|
|
from papis_extract.formatter import (
|
|
format_count,
|
|
format_csv,
|
|
format_markdown,
|
|
format_markdown_atx,
|
|
format_markdown_setext,
|
|
)
|
|
|
|
document = Document(data={"author": "document-author", "title": "document-title"})
|
|
annotations = [
|
|
Annotation("myfile.pdf", text="my lovely text"),
|
|
Annotation("myfile.pdf", text="my second text", content="with note"),
|
|
]
|
|
md_default_output = """============== ---------------
|
|
document-title - document-author
|
|
============== ---------------
|
|
|
|
> my lovely text
|
|
|
|
> my second text
|
|
NOTE: with note"""
|
|
|
|
|
|
def test_markdown_default():
|
|
fmt = format_markdown
|
|
assert fmt(document, annotations) == md_default_output
|
|
|
|
|
|
def test_markdown_atx():
|
|
fmt = format_markdown_atx
|
|
assert fmt(document, annotations) == (
|
|
"""# document-title - document-author
|
|
|
|
> my lovely text
|
|
|
|
> my second text
|
|
NOTE: with note"""
|
|
)
|
|
|
|
|
|
def test_markdown_setext():
|
|
fmt = format_markdown_setext
|
|
assert fmt(document, annotations) == md_default_output
|
|
|
|
|
|
def test_count_default():
|
|
fmt = format_count
|
|
assert fmt(document, annotations) == ("""document-author - document-title: 2""")
|
|
|
|
|
|
def test_csv_default():
|
|
fmt = format_csv
|
|
assert fmt(document, annotations) == (
|
|
"type,tag,page,quote,note,author,title,ref,file\n"
|
|
'Highlight,,0,"my lovely text","","document-author",'
|
|
'"document-title","","myfile.pdf"\n'
|
|
'Highlight,,0,"my second text","with note","document-author",'
|
|
'"document-title","","myfile.pdf"'
|
|
)
|
|
|
|
|
|
# sadpath - no annotations contained for each format
|
|
def test_markdown_no_annotations():
|
|
assert format_markdown(document, []) == ""
|
|
|
|
|
|
def test_count_no_annotations():
|
|
assert format_count(document, []) == ""
|
|
|
|
|
|
def test_csv_no_annotations():
|
|
assert format_csv(document, []) == ""
|