papis-extract/papis_extract/annotation.py

84 lines
2.6 KiB
Python
Raw Normal View History

2023-08-28 08:28:06 +00:00
import math
from dataclasses import dataclass, field
import papis.config
from papis.document import Document
import chevron
2023-08-28 08:28:06 +00:00
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:
2023-09-19 15:52:45 +00:00
"""A PDF annotation object.
Contains all information necessary for the annotation itself, content and metadata.
"""
2023-08-28 08:28:06 +00:00
file: str
colors: tuple[float, float, float] = field(default_factory=lambda: (0.0, 0.0, 0.0))
content: str = ""
page: int = 0
2023-08-28 08:28:06 +00:00
tag: str = ""
text: str = ""
type: str = "Highlight"
minimum_similarity_color: float = 1.0
2023-08-28 08:28:06 +00:00
def format(self, formatting: str, doc: Document = Document()):
2023-08-28 08:28:06 +00:00
"""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,
2023-08-28 08:28:06 +00:00
}
return chevron.render(formatting, data)
2023-08-28 08:28:06 +00:00
@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.
"""
2023-08-31 19:32:24 +00:00
annot_colors = self.colors or (0.0, 0.0, 0.0)
2023-08-28 08:28:06 +00:00
nearest = None
minimum_similarity = (
2023-08-28 10:55:01 +00:00
papis.config.getfloat("minimum_similarity_color", "plugins.extract") or 1.0
2023-08-28 08:28:06 +00:00
)
minimum_similarity = self.minimum_similarity_color
2023-08-28 08:28:06 +00:00
for name, values in COLORS.items():
similarity_ratio = self._color_similarity_ratio(values, annot_colors)
if similarity_ratio >= minimum_similarity:
2023-08-28 08:28:06 +00:00
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)