diff --git a/CHANGELOG.md b/CHANGELOG.md index 0e8a8671..512370f4 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,3 +1,7 @@ +## PLAYA 0.2.6: Unreleased +- Correct some type annotations (these were not really bugs) +- Handle more CMap and ToUnicode corner cases + ## PLAYA 0.2.5: 2024-12-15 - Fix various bugs in the lazy API - Add specialized `__len__` methods to ContentObject classes diff --git a/TODO.md b/TODO.md index 1ddbb9cc..43555b9e 100644 --- a/TODO.md +++ b/TODO.md @@ -6,6 +6,8 @@ ## PLAYA 0.2.x - [ ] work around invalid ToUnicode CMaps + - Implement and test all special cases from pdf.js readToUniocde + - Debug/trace pdf.js on the cases noted in tests/data.py - [ ] `decode_text` is remarkably slow - [ ] `render_char` and `render_string` are also quite slow - [ ] add something inbetween `chars` and full bbox for TextObject diff --git a/benchmarks/converter.py b/benchmarks/converter.py index 4635ca57..c18689c0 100644 --- a/benchmarks/converter.py +++ b/benchmarks/converter.py @@ -6,7 +6,7 @@ import sys import time from pathlib import Path -from tests.data import TESTDIR, BASEPDFS, PASSWORDS, XFAILS, CONTRIB +from tests.data import BASEPDFS, PASSWORDS, XFAILS from tests.test_open import PDFMINER_BUGS LOG = logging.getLogger("benchmark-convert")