NEXTPY-569 -- Make pdfquery compatible with Python 3.9 and 3.11

.travis.yml

@@ -1,23 +1,18 @@
 language: python
 python:
-  - "3.5"
-  - "3.6"
-  - "3.7"
-  - "3.8"
+  - "3.9"
+  - "3.11"
 env: CFLAGS="-O0"
 
 cache:
   directories:
     - $HOME/.cache/pip
 
 install:
-  - if [[ $TRAVIS_PYTHON_VERSION < 3 ]]; then pip install -r requirements_py2.txt; fi
-  - if [[ $TRAVIS_PYTHON_VERSION > 3 ]]; then pip install -r requirements_py3.txt; fi
-  - if [[ $TRAVIS_PYTHON_VERSION == '2.6' ]]; then pip install unittest2; fi
-script:
-  python setup.py test
+  - pip install -e .
+script: python setup.py test
 after_success:
   - coveralls
 
 # See: http://docs.travis-ci.com/user/migrating-from-legacy/
-sudo: false
+sudo: false

CHANGES.txt

@@ -1,3 +1,18 @@
+v0.5.0, 2021-05-03 -- 
+0.5.1 (unreleased)
+
+
+- Make pdfquery compatible with Python 3.9 and 3.11
+
+
+0.5.0 (2021-05-04)
+    - #67 Fix range() page numbers for Python3 & prevent long cache file names
+    - Remove references to old version of PDFMiner
+    - Fixed an isort issue
+    - Update (un)supported Python versions
+    - Improve performance on large pdfs
+    - Remove reference to deprecated easy_install
+    - Fix two broken testcases
 v0.4.3, 2016-03-27 -- Add laparams parameter to __init__.
 v0.4.2, 2016-02-07 -- Annotations bugfix.
 v0.4.1, 2015-12-21 -- Annotations bugfix.

README.rst

@@ -18,10 +18,16 @@ PDFs with as little code as possible.
 
 .. contents:: **Table of Contents**
 
-Installation
-============
+Installation as a package
+=========================
+
+``pip install pdfquery``
+
+
+Installation for development
+============================
 
-``easy_install pdfquery`` or ``pip install pdfquery``.
+``pip install -e ".[test,flake8,docs,release]"``
 
 Quick Start
 ===========

appveyor.yml

@@ -1,13 +1,9 @@
 environment:
   matrix:
-    # https://www.appveyor.com/docs/windows-images-software/#python
-    # currently lxml does not successfully install in 3.5 and 3.8
-#    - PYTHON: "C:\\Python35"
-    - PYTHON: "C:\\Python36"
-    - PYTHON: "C:\\Python37"
-#    - PYTHON: "C:\\Python38"
+    - PYTHON: "C:\\Python39"
+    - PYTHON: "C:\\Python311"
 
 build: off
 
 test_script:
-  - "%PYTHON%\\python.exe setup.py test"
+  - "%PYTHON%\\python.exe setup.py test"

pdfquery/__init__.py

@@ -1 +1 @@
-from .pdfquery import PDFQuery
+from .pdfquery import PDFQuery

pdfquery/cache.py

@@ -1,9 +1,10 @@
 import hashlib
 import zipfile
+
 from lxml import etree
 
-class BaseCache(object):
 
+class BaseCache(object):
     def __init__(self):
         self.hash_key = None
 
@@ -32,30 +33,34 @@ class DummyCache(BaseCache):
 
 
 class FileCache(BaseCache):
-
-    def __init__(self, directory='/tmp/'):
+    def __init__(self, directory="/tmp/"):
         self.directory = directory
         super(FileCache, self).__init__()
 
     def get_cache_filename(self, page_range_key):
         return "pdfquery_{hash_key}{page_range_key}.xml".format(
-            hash_key=self.hash_key,
-            page_range_key=page_range_key
+            hash_key=self.hash_key, page_range_key=page_range_key
         )
 
     def get_cache_file(self, page_range_key, mode):
         try:
-            return zipfile.ZipFile(self.directory+self.get_cache_filename(page_range_key)+".zip", mode)
+            return zipfile.ZipFile(
+                self.directory + self.get_cache_filename(page_range_key) + ".zip", mode
+            )
         except IOError:
             return None
 
     def set(self, page_range_key, tree):
-        xml = etree.tostring(tree, encoding='utf-8', pretty_print=False, xml_declaration=True)
-        cache_file = self.get_cache_file(page_range_key, 'w')
+        xml = etree.tostring(
+            tree, encoding="utf-8", pretty_print=False, xml_declaration=True
+        )
+        cache_file = self.get_cache_file(page_range_key, "w")
         cache_file.writestr(self.get_cache_filename(page_range_key), xml)
         cache_file.close()
 
     def get(self, page_range_key):
-        cache_file = self.get_cache_file(page_range_key, 'r')
+        cache_file = self.get_cache_file(page_range_key, "r")
         if cache_file:
-            return etree.fromstring(cache_file.read(self.get_cache_filename(page_range_key)))
+            return etree.fromstring(
+                cache_file.read(self.get_cache_filename(page_range_key))
+            )