From 6b35b2f918f06a36c67d5b36f7594bb26892e744 Mon Sep 17 00:00:00 2001
From: Marty Oehme <marty.oehme@gmail.com>
Date: Fri, 14 Jun 2024 15:13:24 +0200
Subject: [PATCH] chore: Fix strict pyright analysis errors

---
 papis_extract/annotation.py            |  6 +++---
 papis_extract/extractors/pdf.py        | 12 ++++++++----
 papis_extract/extractors/pocketbook.py | 22 ++++++++++++++++------
 tests/test_annotation.py               |  6 +++---
 4 files changed, 30 insertions(+), 16 deletions(-)

diff --git a/papis_extract/annotation.py b/papis_extract/annotation.py
index 666c1bb..54b216d 100644
--- a/papis_extract/annotation.py
+++ b/papis_extract/annotation.py
@@ -1,6 +1,6 @@
 import math
 from dataclasses import dataclass
-from typing import Any, Optional
+from typing import Any, Optional, cast
 
 import chevron
 import papis.config
@@ -127,7 +127,7 @@ class Annotation:
         """
         rawvalue: Any = papis.config.general_get(key, section=section)
         if isinstance(rawvalue, dict):
-            return rawvalue
+            return cast(dict[str, str], rawvalue)
         try:
             rawvalue = eval(rawvalue)
         except Exception:
@@ -142,4 +142,4 @@ class Annotation:
                     )
                 )
 
-            return rawvalue
+            return cast(dict[str, str], rawvalue)
diff --git a/papis_extract/extractors/pdf.py b/papis_extract/extractors/pdf.py
index f61cefc..55c13f1 100644
--- a/papis_extract/extractors/pdf.py
+++ b/papis_extract/extractors/pdf.py
@@ -1,10 +1,12 @@
+# pyright: strict, reportMissingTypeStubs=false, reportUnknownMemberType=false
 from pathlib import Path
+from typing import cast
 
-import fitz
 import Levenshtein
 import magic
 import papis.config
 import papis.logging
+import pymupdf as mu
 
 from papis_extract.annotation import Annotation
 from papis_extract.extractors import ExtractionError
@@ -30,7 +32,9 @@ class PdfExtractor:
         annotations: list[Annotation] = []
         try:
             with mu.Document(filename) as doc:
-                for page in doc:  # pyright: ignore [reportUnknownVariableType] - missing stub
+                for (
+                    page
+                ) in doc:  # pyright: ignore [reportUnknownVariableType] - missing stub
                     page = cast(mu.Page, page)
                     annot: mu.Annot
                     for annot in page.annots():
@@ -61,7 +65,7 @@ class PdfExtractor:
                 f"{'annotation' if len(annotations) == 1 else 'annotations'} for {filename}."
             )
 
-        except mu.FileDataError as e:
+        except mu.FileDataError:
             raise ExtractionError
 
         return annotations
@@ -82,7 +86,7 @@ class PdfExtractor:
         should both be included or are the same, using
         Levenshtein distance.
         """
-        content = annotation.info["content"].replace("\n", " ")
+        content = cast(str, annotation.info["content"].replace("\n", " "))
         written = page.get_textbox(annotation.rect).replace("\n", " ")
 
         # highlight with selection in note
diff --git a/papis_extract/extractors/pocketbook.py b/papis_extract/extractors/pocketbook.py
index 56ab17c..ad73ad7 100644
--- a/papis_extract/extractors/pocketbook.py
+++ b/papis_extract/extractors/pocketbook.py
@@ -1,3 +1,4 @@
+# pyright: strict, reportUnknownMemberType=false
 from pathlib import Path
 
 import magic
@@ -42,9 +43,18 @@ class PocketBookExtractor:
 
         annotations: list[Annotation] = []
         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
+            content = str(
+                (bm.select_one("div.bm-text>p") or html.new_string("")).text
+                or ""  # pyright: ignore [reportUnknownArgumentType]
+            )
+            note = str(
+                (bm.select_one("div.bm-note>p") or html.new_string("")).text
+                or ""  # pyright: ignore [reportUnknownArgumentType]
+            )
+            page = int(
+                (bm.select_one("p.bm-page") or html.new_string("")).text
+                or 0  # pyright: ignore [reportUnknownArgumentType]
+            )
 
             el_classes = bm.attrs.get("class", "").split(" ")
             color = (0, 0, 0)
@@ -55,11 +65,11 @@ class PocketBookExtractor:
 
             a = Annotation(
                 file=str(filename),
-                content=content or "",
-                note=note or "",
+                content=content,
+                note=note,
                 color=color,
                 type="Highlight",
-                page=int(page),
+                page=page,
             )
             annotations.append(a)
 
diff --git a/tests/test_annotation.py b/tests/test_annotation.py
index 98e7f31..ceb0c0e 100644
--- a/tests/test_annotation.py
+++ b/tests/test_annotation.py
@@ -18,7 +18,7 @@ from papis_extract.annotation import Annotation
         ),
     ],
 )
-def test_formatting_replacements(fmt_string, expected):
+def test_formatting_replacements(fmt_string: str, expected: str):
     sut = Annotation(
         "myfile",
         content="I am the text value",
@@ -36,7 +36,7 @@ def test_formatting_replacements(fmt_string, expected):
         ("{{quote}} ({{doc.author}})", "I am the text value (document-author)"),
     ],
 )
-def test_formatting_document_access(fmt_string, expected):
+def test_formatting_document_access(fmt_string: str, expected: str):
     sut = Annotation(
         "myfile",
         content="I am the text value",
@@ -64,7 +64,7 @@ def test_colorname_matches_exact():
         (0.51, 0.0, 0.0),
     ],
 )
-def test_matches_inexact_colorname(color_value):
+def test_matches_inexact_colorname(color_value: tuple[float, float, float]):
     sut = Annotation("testfile", color=color_value, minimum_similarity_color=0.833)
     c_name = sut.colorname
     assert c_name == "red"