From 69e5df87789b7adc25968703461d7c08790f8773 Mon Sep 17 00:00:00 2001
From: Jan-Christoph Klie <git@mrklie.com>
Date: Thu, 21 Apr 2022 10:10:49 +0200
Subject: [PATCH 1/7] No issue - Fix test

It broke because the Bavarian Wiki got updated.
---
 tests/test_mapper.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tests/test_mapper.py b/tests/test_mapper.py
index f5de261..205c643 100644
--- a/tests/test_mapper.py
+++ b/tests/test_mapper.py
@@ -12,7 +12,7 @@
     pytest.param("Quadrátkilometa", "Q25343", id="Has redirect"),
     pytest.param("D'_boarische_Woocha", "Q20616808", id="Has special character"),
     pytest.param("I am not in the Wiki", None, id="Title not in the wiki"),
-    pytest.param("Pergentinus_und_Laurentinus", None, id="In the index, but not mapped"),
+    pytest.param("tungsten", None, id="In the index, but not mapped"),
 ]
 
 

From 1d042151796d55e3bfc8efcd8285a528f97485b6 Mon Sep 17 00:00:00 2001
From: Jan-Christoph Klie <git@mrklie.com>
Date: Thu, 21 Apr 2022 10:14:56 +0200
Subject: [PATCH 2/7] #7 - Avoiding Overflow Error when Building Index on
 Windows

On Windows, csv maxsize is 32bit, on Linux, it is more often than not 64bit. Therefore, we use a hack to determine the correct size.
---
 wikimapper/processor.py | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/wikimapper/processor.py b/wikimapper/processor.py
index 024ddd0..b1f5179 100644
--- a/wikimapper/processor.py
+++ b/wikimapper/processor.py
@@ -7,7 +7,7 @@
 import logging
 import os
 import sqlite3
-import sys
+import ctypes as ct
 
 _logger = logging.getLogger(__name__)
 
@@ -114,7 +114,8 @@ def create_index(dumpname: str, path_to_dumps: str, path_to_db: str = None) -> s
     page_props_dump = os.path.join(path_to_dumps, dumpname + "-page_props.sql.gz")
     redirects_dump = os.path.join(path_to_dumps, dumpname + "-redirect.sql.gz")
 
-    csv.field_size_limit(sys.maxsize)
+    # https://stackoverflow.com/a/54517228
+    csv.field_size_limit(int(ct.c_ulong(-1).value // 2))
 
     # (Re)Create the database file
     try:

From 552d8f5d6b2dc1b892c31b392a31317b5df267ae Mon Sep 17 00:00:00 2001
From: Jan-Christoph Klie <git@mrklie.com>
Date: Thu, 21 Apr 2022 10:17:02 +0200
Subject: [PATCH 3/7] No issue - Move fixtures to conftest

We then do not need to import it, as pytest does that magically for us.
---
 tests/{fixtures.py => conftest.py} | 0
 tests/test_mapper.py               | 1 -
 tests/test_processor.py            | 1 -
 3 files changed, 2 deletions(-)
 rename tests/{fixtures.py => conftest.py} (100%)

diff --git a/tests/fixtures.py b/tests/conftest.py
similarity index 100%
rename from tests/fixtures.py
rename to tests/conftest.py
diff --git a/tests/test_mapper.py b/tests/test_mapper.py
index 205c643..18f6693 100644
--- a/tests/test_mapper.py
+++ b/tests/test_mapper.py
@@ -1,6 +1,5 @@
 import pytest
 
-from tests.fixtures import *
 
 BAVARIAN_PARAMS = [
     pytest.param("Stoaboog", "Q168327"),
diff --git a/tests/test_processor.py b/tests/test_processor.py
index 30109be..6071b37 100644
--- a/tests/test_processor.py
+++ b/tests/test_processor.py
@@ -3,7 +3,6 @@
 
 from wikimapper import create_index
 
-from tests.fixtures import *
 
 
 def test_create_index(tmpdir, bavarian_wiki_dump):

From 1ea7debb90550ce319cc3da6cb45222c7532453c Mon Sep 17 00:00:00 2001
From: Jan-Christoph Klie <git@mrklie.com>
Date: Thu, 21 Apr 2022 10:19:19 +0200
Subject: [PATCH 4/7] No issue - Format files and isort

---
 Makefile                | 5 +++++
 setup.py                | 1 +
 tests/conftest.py       | 6 ++----
 tests/test_mapper.py    | 1 -
 tests/test_processor.py | 1 -
 wikimapper/cli.py       | 6 +++---
 wikimapper/download.py  | 4 ++--
 wikimapper/mapper.py    | 8 ++++----
 wikimapper/processor.py | 4 ++--
 9 files changed, 19 insertions(+), 17 deletions(-)

diff --git a/Makefile b/Makefile
index ea328d1..eefab82 100644
--- a/Makefile
+++ b/Makefile
@@ -5,5 +5,10 @@ black:
 	black -l 100 wikimapper/
 	black -l 100 tests/
 
+isort:
+	isort --profile black wikimapper/ tests/
+
+format: black isort
+
 html:
 	cd docs && make html
\ No newline at end of file
diff --git a/setup.py b/setup.py
index ad26501..993fe8a 100644
--- a/setup.py
+++ b/setup.py
@@ -30,6 +30,7 @@
 
 dev_dependencies = [
     "black",
+    "isort",
     "twine",
     "pygments",
     "wheel"
diff --git a/tests/conftest.py b/tests/conftest.py
index 4c2ce38..0a08a3a 100644
--- a/tests/conftest.py
+++ b/tests/conftest.py
@@ -1,17 +1,15 @@
 from collections import namedtuple
-import os
 
 import pytest
 
-from wikimapper import download_wikidumps, create_index, WikiMapper
-
+from wikimapper import WikiMapper, create_index, download_wikidumps
 
 Wiki = namedtuple("Wiki", ["dumpname", "path"])
 
 
 @pytest.fixture(scope="package")
 def bavarian_wiki_dump(tmpdir_factory) -> Wiki:
-    """ We download the Bavarian Wiki, as it is quite small. """
+    """We download the Bavarian Wiki, as it is quite small."""
 
     dumpname = "barwiki-latest"
     path = tmpdir_factory.mktemp("dumps").strpath
diff --git a/tests/test_mapper.py b/tests/test_mapper.py
index 18f6693..866d0f3 100644
--- a/tests/test_mapper.py
+++ b/tests/test_mapper.py
@@ -1,6 +1,5 @@
 import pytest
 
-
 BAVARIAN_PARAMS = [
     pytest.param("Stoaboog", "Q168327"),
     pytest.param("Wechslkrod", "Q243242"),
diff --git a/tests/test_processor.py b/tests/test_processor.py
index 6071b37..aaa5274 100644
--- a/tests/test_processor.py
+++ b/tests/test_processor.py
@@ -4,7 +4,6 @@
 from wikimapper import create_index
 
 
-
 def test_create_index(tmpdir, bavarian_wiki_dump):
     path_to_db = tmpdir.mkdir("processor").join("index_test.db").strpath
 
diff --git a/wikimapper/cli.py b/wikimapper/cli.py
index 1c43d06..6624b76 100644
--- a/wikimapper/cli.py
+++ b/wikimapper/cli.py
@@ -2,8 +2,8 @@
 import logging
 import os
 
+from wikimapper import WikiMapper, create_index, download_wikidumps
 from wikimapper.__version__ import __version__
-from wikimapper import download_wikidumps, create_index, WikiMapper
 
 
 def main():
@@ -126,7 +126,7 @@ def main():
 
 
 def _dir_path(path) -> str:
-    """ Checks whether `path` is a valid path to a directory. """
+    """Checks whether `path` is a valid path to a directory."""
     if os.path.isdir(path):
         return path
     else:
@@ -134,7 +134,7 @@ def _dir_path(path) -> str:
 
 
 def _dump_name(name) -> str:
-    """ Checks whether `name` is a valid Wikipedia dump name. """
+    """Checks whether `name` is a valid Wikipedia dump name."""
     parts = name.split("-")
     err = lambda: argparse.ArgumentTypeError(f"dumpname: [{name}] is not a valid dump name")
 
diff --git a/wikimapper/download.py b/wikimapper/download.py
index b9b5405..28766fb 100644
--- a/wikimapper/download.py
+++ b/wikimapper/download.py
@@ -14,7 +14,7 @@ def _report_hook(count: int, block_size: int, total_size: int):
 
 
 def _download_file(url: str, target: str, overwrite: bool):
-    """ Downloads the content identified by `url` and saves it in `target`."""
+    """Downloads the content identified by `url` and saves it in `target`."""
     if os.path.exists(target) and not overwrite:
         _logger.info("[%s] already exists, skipping downloading [%s]!", target, url)
         return
@@ -29,7 +29,7 @@ def _download_file(url: str, target: str, overwrite: bool):
 def download_wikidumps(
     dumpname: str, path: str, mirror: str = "https://dumps.wikimedia.org/", overwrite: bool = False
 ):
-    """ Downloads pages, page props and redirect SQL dumps for the dump
+    """Downloads pages, page props and redirect SQL dumps for the dump
     specified by `dumpname` to the folder `path`. If `overwrite` is true,
     then it is downloaded again even if the files already exist.
 
diff --git a/wikimapper/mapper.py b/wikimapper/mapper.py
index 3572d09..ae296e5 100644
--- a/wikimapper/mapper.py
+++ b/wikimapper/mapper.py
@@ -3,13 +3,13 @@
 
 
 class WikiMapper:
-    """ Uses a precomputed database created by `create_wikipedia_wikidata_mapping_db`. """
+    """Uses a precomputed database created by `create_wikipedia_wikidata_mapping_db`."""
 
     def __init__(self, path_to_db: str):
         self._path_to_db = path_to_db
 
     def title_to_id(self, page_title: str) -> Optional[str]:
-        """ Given a Wikipedia page title, returns the corresponding Wikidata ID.
+        """Given a Wikipedia page title, returns the corresponding Wikidata ID.
 
         The page title is the last part of a Wikipedia url **unescaped** and spaces
         replaced by underscores , e.g. for `https://en.wikipedia.org/wiki/Fermat%27s_Last_Theorem`,
@@ -35,7 +35,7 @@ def title_to_id(self, page_title: str) -> Optional[str]:
             return None
 
     def url_to_id(self, wiki_url: str) -> Optional[str]:
-        """ Given an URL to a Wikipedia page, returns the corresponding Wikidata ID.
+        """Given an URL to a Wikipedia page, returns the corresponding Wikidata ID.
 
         This is just a convenience function. It is not checked whether the index and
         URL are from the same dump.
@@ -53,7 +53,7 @@ def url_to_id(self, wiki_url: str) -> Optional[str]:
         return self.title_to_id(title)
 
     def id_to_titles(self, wikidata_id: str) -> List[str]:
-        """ Given a Wikidata ID, return a list of corresponding pages that are linked to it.
+        """Given a Wikidata ID, return a list of corresponding pages that are linked to it.
 
         Due to redirects, the mapping from Wikidata ID to Wikipedia title is not unique.
 
diff --git a/wikimapper/processor.py b/wikimapper/processor.py
index b1f5179..e7dee2b 100644
--- a/wikimapper/processor.py
+++ b/wikimapper/processor.py
@@ -3,11 +3,11 @@
 """
 
 import csv
+import ctypes as ct
 import gzip
 import logging
 import os
 import sqlite3
-import ctypes as ct
 
 _logger = logging.getLogger(__name__)
 
@@ -91,7 +91,7 @@ def _parse_values(values):
 
 
 def create_index(dumpname: str, path_to_dumps: str, path_to_db: str = None) -> str:
-    """ Creates an index mapping Wikipedia page titles to Wikidata IDs and vice versa.
+    """Creates an index mapping Wikipedia page titles to Wikidata IDs and vice versa.
     This requires a previously downloaded dump `dumpname` in `path_to_dumps`.
 
     Args:

From 8aa10478bc79c2e37320cd76ffa33cedaeace189 Mon Sep 17 00:00:00 2001
From: Jan-Christoph Klie <git@mrklie.com>
Date: Thu, 21 Apr 2022 10:26:46 +0200
Subject: [PATCH 5/7] No issue - Remove travis, add Github actions

---
 .coveragerc                     |  7 -------
 .github/workflows/run_tests.yml | 29 +++++++++++++++++++++++++++++
 .travis.yml                     | 14 --------------
 tox.ini                         |  9 ---------
 4 files changed, 29 insertions(+), 30 deletions(-)
 delete mode 100644 .coveragerc
 create mode 100644 .github/workflows/run_tests.yml
 delete mode 100644 .travis.yml
 delete mode 100644 tox.ini

diff --git a/.coveragerc b/.coveragerc
deleted file mode 100644
index 5f23af4..0000000
--- a/.coveragerc
+++ /dev/null
@@ -1,7 +0,0 @@
-[run]
-source=wikimapper
-omit=
-    setup.py
-    wikimapper/__init__.py
-    wikimapper/__version__.py
-    wikimapper/cli.py
\ No newline at end of file
diff --git a/.github/workflows/run_tests.yml b/.github/workflows/run_tests.yml
new file mode 100644
index 0000000..4eedc0e
--- /dev/null
+++ b/.github/workflows/run_tests.yml
@@ -0,0 +1,29 @@
+name: Run Tests
+
+on:
+  push:
+    branches: [ main ]
+  pull_request:
+    branches: [ main ]
+
+jobs:
+  build:
+
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        os: [ubuntu-latest, windows-latest]
+        python-version: [3.7, 3.8, 3.9, 3.10]
+
+    steps:
+    - uses: actions/checkout@v2
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v2
+      with:
+        python-version: ${{ matrix.python-version }}
+    - name: Install dependencies
+      run: |
+        pip install --upgrade -e .[test]
+    - name: Run tests
+      run: |
+        pytest
diff --git a/.travis.yml b/.travis.yml
deleted file mode 100644
index 58a0c1b..0000000
--- a/.travis.yml
+++ /dev/null
@@ -1,14 +0,0 @@
-language: python
-
-python:
- - "3.5"
- - "3.6"
- - "3.7-dev"
-
-install:
-    - pip install --upgrade -e .[test]
-script:
-    - pytest --cov=./
-
-after_success:
-    - codecov
\ No newline at end of file
diff --git a/tox.ini b/tox.ini
deleted file mode 100644
index 809383f..0000000
--- a/tox.ini
+++ /dev/null
@@ -1,9 +0,0 @@
-[tox]
-skipsdist = True
-skip_missing_interpreters = True
-envlist = py35, py36, py37, py38dev
-
-[testenv]
-whitelist_externals=make
-commands = make test
-deps = .[test]
\ No newline at end of file

From 7f2648899d7a5fd04f073eebf08271c2ab0b86af Mon Sep 17 00:00:00 2001
From: Jan-Christoph Klie <git@mrklie.com>
Date: Thu, 21 Apr 2022 10:28:12 +0200
Subject: [PATCH 6/7] No issue - Remove travis, add Github actions

---
 .github/workflows/run_tests.yml | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/.github/workflows/run_tests.yml b/.github/workflows/run_tests.yml
index 4eedc0e..7cb3c3e 100644
--- a/.github/workflows/run_tests.yml
+++ b/.github/workflows/run_tests.yml
@@ -2,9 +2,9 @@ name: Run Tests
 
 on:
   push:
-    branches: [ main ]
+    branches: [ master ]
   pull_request:
-    branches: [ main ]
+    branches: [ master ]
 
 jobs:
   build:

From 056e73bd358ebbb781a6eecaa15f37516c0cc2fe Mon Sep 17 00:00:00 2001
From: Jan-Christoph Klie <git@mrklie.com>
Date: Thu, 21 Apr 2022 10:29:50 +0200
Subject: [PATCH 7/7] No issue - Remove unneeded dependencies

---
 .github/workflows/run_tests.yml | 2 +-
 setup.py                        | 3 ---
 2 files changed, 1 insertion(+), 4 deletions(-)

diff --git a/.github/workflows/run_tests.yml b/.github/workflows/run_tests.yml
index 7cb3c3e..1eeaa02 100644
--- a/.github/workflows/run_tests.yml
+++ b/.github/workflows/run_tests.yml
@@ -13,7 +13,7 @@ jobs:
     strategy:
       matrix:
         os: [ubuntu-latest, windows-latest]
-        python-version: [3.7, 3.8, 3.9, 3.10]
+        python-version: [3.7, 3.8, 3.9]
 
     steps:
     - uses: actions/checkout@v2
diff --git a/setup.py b/setup.py
index 993fe8a..946daef 100644
--- a/setup.py
+++ b/setup.py
@@ -22,10 +22,7 @@
 install_requires=[]
 
 test_dependencies = [
-    "tox",
     "pytest",
-    "codecov",
-    "pytest-cov",
 ]
 
 dev_dependencies = [