papis-extract/papis_extract/annotation_data.py
Marty Oehme 5a6d672c76
refactor: Move formatting logic to formatters
Formatters (previously templates) were pure data containers before,
continating the 'template' for how things should be formatted using
mustache. The formatting would be done a) in the exporters and b) in the
annotations.

This spread of formatting has now been consolidated into the Formatter,
which fixes the overall spread of formatting code and now can coherently
format a whole output instead of just individual annotations.

A formatter contains references to all documents and contained
annotations and will format everything at once by default, but the
formatting function can be invoked with reference to a specific
annotated document to only format that.

This commit should put more separation into the concerns of exporter and
formatter and made formatting a concern purely of the formatters and
annotation objects.
2023-09-20 09:14:58 +02:00

95 lines
2.9 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, template: 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(template, 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)
@dataclass
class AnnotatedDocument:
"""Contains all annotations belonging to a single papis document.
Combines a document with a list of annotations which belong to it."""
document: Document
annotations: list[Annotation]
# TODO could implement a from_doc() static method to generate annotation list?