chore: Remove python-magic dependency

It relies on the libmagic module which is not necessarily installed
everywhere. Most of the functionality that we need for our purposes can
be recreated with lighter-weight methods.

papis_extract/extractors/pdf.py

@@ -1,10 +1,10 @@
 # pyright: strict, reportMissingTypeStubs=false, reportUnknownMemberType=false
+import mimetypes
 from collections.abc import Generator
 from pathlib import Path
 from typing import NamedTuple, cast
 
 import Levenshtein
-import magic
 import papis.config
 import papis.logging
 import pymupdf as mu
@@ -77,7 +77,7 @@ class PdfExtractor:
 
     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"
+        return mimetypes.guess_type(fname)[0] == "application/pdf"
 
     def _get_annotation_content(
         self, page: mu.Page, annotation: mu.Annot

papis_extract/extractors/pocketbook.py

@@ -1,7 +1,7 @@
 # pyright: strict, reportUnknownMemberType=false
+import mimetypes
 from pathlib import Path
 
-import magic
 import papis.logging
 from bs4 import BeautifulSoup
 
@@ -12,7 +12,7 @@ logger = papis.logging.get_logger(__name__)
 
 class PocketBookExtractor:
     def can_process(self, filename: Path) -> bool:
-        if magic.from_file(filename, mime=True) != "text/xml":
+        if not self._is_html(filename):
             return False
 
         content = self._read_file(filename)
@@ -28,6 +28,9 @@ class PocketBookExtractor:
         logger.debug(f"Found processable annotation file: {filename}")
         return True
 
+    def _is_html(self, filename: Path) -> bool:
+        return mimetypes.guess_type(filename)[0] == "text/html"
+
     def run(self, filename: Path) -> list[Annotation]:
         """Extract annotations from pocketbook html file.
 

papis_extract/extractors/readera.py

@@ -1,8 +1,8 @@
 # pyright: strict, reportUnknownMemberType=false
+import mimetypes
 import re
 from pathlib import Path
 
-import magic
 import papis.logging
 
 from papis_extract.annotation import Annotation
@@ -17,7 +17,7 @@ class ReadEraExtractor:
     """
 
     def can_process(self, filename: Path) -> bool:
-        if magic.from_file(filename, mime=True) != "text/plain":
+        if not self._is_txt(filename):
             return False
 
         content = self._read_file(filename)
@@ -36,11 +36,12 @@ class ReadEraExtractor:
         if not re.search(r"\n\*\*\*\*\*\n\n$", "".join(content)):
             return False
 
-        logger.debug(
-            f"Found processable annotation file: {filename}"
-        )
+        logger.debug(f"Found processable annotation file: {filename}")
         return True
 
+    def _is_txt(self, filename: Path) -> bool:
+        return mimetypes.guess_type(filename)[0] == "text/plain"
+
     def run(self, filename: Path) -> list[Annotation]:
         """Extract annotations from readera txt file.
 

papis_extract/extractors/readest.py

@@ -2,13 +2,15 @@
 import re
 from pathlib import Path
 
-import magic
 import papis.logging
 
 from papis_extract.annotation import Annotation
 
 logger = papis.logging.get_logger(__name__)
 
+ACCEPTED_EXTENSIONS = [".txt", ".md", ".qmd", ".rmd"]
+TEXTCHARS = bytearray({7, 8, 9, 10, 12, 13, 27} | set(range(0x20, 0x100)) - {0x7F})
+
 
 class ReadestExtractor:
     """Extracts exported annotations from the FOSS Readest book reading app.
@@ -17,7 +19,7 @@ class ReadestExtractor:
     """
 
     def can_process(self, filename: Path) -> bool:
-        if magic.from_file(filename, mime=True) != "text/plain":
+        if not self._is_readable_text(filename):
             return False
 
         content = self._read_file(filename)
@@ -33,6 +35,22 @@ class ReadestExtractor:
         logger.debug(f"Found processable annotation file: {filename}")
         return True
 
+    def _is_readable_text(self, filename: Path) -> bool:
+        """Checks whether a file has a valid text extension and is not a binary file.
+
+        A file is considered a valid text file if its extension is in
+        :data:`ACCEPTED_EXTENSIONS` and does not contain any non-text characters.
+
+        :returns: A boolean indicating whether the file is a valid text file.
+        """
+        if filename.suffix not in ACCEPTED_EXTENSIONS:
+            return False
+        try:
+            with filename.open("rb") as rb:
+                return not bool(rb.read(1024).translate(None, TEXTCHARS))
+        except (FileNotFoundError, PermissionError):
+            return False
+
     def run(self, filename: Path) -> list[Annotation]:
         """Extract annotations from readest txt file.
 

pyproject.toml

@@ -22,7 +22,6 @@ keywords = [
     "bibliography",
     "reference manager",
     "research",
-    "science",
 ]
 
 [project.urls]