papis-extract/papis_extract/annotation.py
Marty Oehme 765de505bb
refactor: Remove AnnotatedDocument class
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.
2024-01-20 16:36:24 +01:00

83 lines
2.6 KiB
Python

import math
from dataclasses import dataclass, field
import papis.config
from papis.document import Document
import chevron
TEXT_SIMILARITY_MINIMUM = 0.75
COLOR_SIMILARITY_MINIMUM = 0.833
COLORS = {
"red": (1, 0, 0),
"green": (0, 1, 0),
"blue": (0, 0, 1),
"yellow": (1, 1, 0),
"purple": (0.5, 0, 0.5),
"orange": (1, 0.65, 0),
}
@dataclass
class Annotation:
"""A PDF annotation object.
Contains all information necessary for the annotation itself, content and metadata.
"""
file: str
colors: tuple[float, float, float] = field(default_factory=lambda: (0.0, 0.0, 0.0))
content: str = ""
page: int = 0
tag: str = ""
text: str = ""
type: str = "Highlight"
minimum_similarity_color: float = 1.0
def format(self, formatting: str, doc: Document = Document()):
"""Return a formatted string of the annotation.
Given a provided formatting pattern, this method returns the annotation
formatted with the correct marker replacements and removals, ready
for display or writing.
"""
data = {
"file": self.file,
"quote": self.text,
"note": self.content,
"page": self.page,
"tag": self.tag,
"type": self.type,
"doc": doc,
}
return chevron.render(formatting, data)
@property
def colorname(self):
"""Return the stringified version of the annotation color.
Finds the closest named color to the annotation and returns it,
using euclidian distance between the two color vectors.
"""
annot_colors = self.colors or (0.0, 0.0, 0.0)
nearest = None
minimum_similarity = (
papis.config.getfloat("minimum_similarity_color", "plugins.extract") or 1.0
)
minimum_similarity = self.minimum_similarity_color
for name, values in COLORS.items():
similarity_ratio = self._color_similarity_ratio(values, annot_colors)
if similarity_ratio >= minimum_similarity:
minimum_similarity = similarity_ratio
nearest = name
return nearest
def _color_similarity_ratio(self, color_one, color_two):
"""Return the similarity of two colors between 0 and 1.
Takes two rgb color tuples made of floats between 0 and 1,
e.g. (1, 0.65, 0) for orange, and returns the similarity
between them, with 1 being the same color and 0 being the
difference between full black and full white, as a float.
"""
return 1 - (abs(math.dist([*color_one], [*color_two])) / 3)