feat: Add pocketbook extraction

papis_extract/annotation.py

@@ -9,15 +9,19 @@ from papis.document import Document
 TEXT_SIMILARITY_MINIMUM = 0.75
 COLOR_SIMILARITY_MINIMUM = 0.833
 
-COLORS = {
-    "red": (1, 0, 0),
-    "green": (0, 1, 0),
+COLORS: dict[str, tuple[float, float, float]] = {
     "blue": (0, 0, 1),
+    "green": (0, 1, 0),
+    "red": (1, 0, 0),
+    "cyan": (0, 1, 1),
     "yellow": (1, 1, 0),
+    "magenta": (1, 0, 1),
     "purple": (0.5, 0, 0.5),
+    "pink": (1, 0.75, 0.8),
     "orange": (1, 0.65, 0),
 }
 
+
 @dataclass
 class Annotation:
     """A PDF annotation object.

papis_extract/exporter.py

@@ -98,7 +98,7 @@ def _add_annots_to_note(
         f.write("\n")
         logger.info(
             f"Wrote {len(new_annotations)} "
-            f"{'annotation' if len(new_annotations) == 1 else 'annotations'} "
+            f"{'line' if len(new_annotations) == 1 else 'lines'} "
             f"to {papis.document.describe(document)}"
         )
 

papis_extract/extraction.py

@@ -47,6 +47,6 @@ def start(
     if not file_available:
         # have to remove curlys or papis logger gets upset
         desc = re.sub("[{}]", "", papis.document.describe(document))
-        logger.warning("Did not find suitable file for document: " f"{desc}")
+        logger.info(f"No {type(extractor)} file for document: {desc}")
 
     return annotations

papis_extract/extractors/__init__.py

@@ -1,6 +1,8 @@
 from papis_extract.extraction import Extractor
 from papis_extract.extractors import pdf
+from papis_extract.extractors.pocketbook import PocketBookExtractor
 
 all_extractors: dict[str, Extractor] = {
     "pdf": pdf.PdfExtractor(),
+    "pocketbook": PocketBookExtractor(),
 }

papis_extract/extractors/pdf.py

@@ -1,5 +1,4 @@
 from pathlib import Path
-from typing import Any, Optional
 
 import fitz
 import Levenshtein
@@ -43,7 +42,7 @@ class PdfExtractor:
                         file=str(filename),
                         content=quote or "",
                         note=note or "",
-                        colors=col,
+                        color=col,
                         type=annot.type[1],
                         page=(page.number or 0) + 1,
                     )
@@ -54,14 +53,12 @@ class PdfExtractor:
         )
         return annotations
 
-
     def _is_pdf(self, fname: Path) -> bool:
         """Check if file is a pdf, using mime type."""
         return magic.from_file(fname, mime=True) == "application/pdf"
 
-
-    def _retrieve_annotation_content(self, 
-        page: fitz.Page, annotation: fitz.Annot
+    def _retrieve_annotation_content(
+        self, page: fitz.Page, annotation: fitz.Annot
     ) -> tuple[str | None, str | None]:
         """Gets the text content of an annotation.
 
@@ -77,7 +74,8 @@ class PdfExtractor:
 
         # highlight with selection in note
         minimum_similarity = (
-            papis.config.getfloat("minimum_similarity_content", "plugins.extract") or 1.0
+            papis.config.getfloat("minimum_similarity_content", "plugins.extract")
+            or 1.0
         )
         if Levenshtein.ratio(content, written) > minimum_similarity:
             return (content, None)
@@ -92,5 +90,3 @@ class PdfExtractor:
             return (written, None)
         # just a highlight without any text
         return (None, None)
-
-

papis_extract/extractors/pocketbook.py

@@ -0,0 +1,60 @@
+from pathlib import Path
+
+import magic
+import papis.config
+import papis.logging
+from bs4 import BeautifulSoup
+
+from papis_extract.annotation import COLORS, Annotation
+
+logger = papis.logging.get_logger(__name__)
+
+
+class PocketBookExtractor:
+    def can_process(self, filename: Path) -> bool:
+        return magic.from_file(filename, mime=True) == "text/xml"
+
+    def run(self, filename: Path) -> list[Annotation]:
+        """Extract annotations from pocketbook html file.
+
+        Export annotations from pocketbook app and load add them
+        to a papis document as the exported html file.
+
+        Returns all readable annotations contained in the file
+        passed in, with highlights, notes and pages if available.
+        """
+        annotations: list[Annotation] = []
+        try:
+            with open(filename) as f:
+                html = BeautifulSoup(f.read(), features="xml")
+        except FileNotFoundError:
+            logger.error(f"Could not open file {filename} for extraction.")
+            return []
+
+        for bm in html.select("div.bookmark"):
+            content = (bm.select_one("div.bm-text>p") or html.new_string("")).text
+            note = (bm.select_one("div.bm-note>p") or html.new_string("")).text
+            page = (bm.select_one("p.bm-page") or html.new_string("")).text
+
+            el_classes = bm.attrs.get("class", "").split(" ")
+            color = (0, 0, 0)
+            for c in el_classes:
+                if "bm-color-" in c:
+                    color = COLORS.get(c.removeprefix("bm-color-"), (0, 0, 0))
+                    break
+
+            a = Annotation(
+                file=str(filename),
+                content=content or "",
+                note=note or "",
+                color=color,
+                type="Highlight",
+                page=int(page),
+            )
+            annotations.append(a)
+
+        logger.debug(
+            f"Found {len(annotations)} "
+            f"{'annotation' if len(annotations) == 1 else 'annotations'} for {filename}."
+        )
+        return annotations

pyproject.toml

@@ -19,9 +19,11 @@ click = "^8.1.7"
 whoosh = { version = "^2.7.4", optional = true }
 python-magic = "^0.4.27"
 chevron = "^0.14.0"
+beautifulsoup4 = { version = "^4.12.3", optional = true }
 
 [tool.poetry.extras]
 whoosh = ["whoosh"]
+pocketbook = ["beautifulsoup4"]
 
 [tool.poetry.group.dev.dependencies]
 pytest = "^7.4.0"