Merge pull request #79 from jgehrcke/jp/maintenance

Maintenance: bump dependencies, adjust README, re-generate base image

Dockerfile

@@ -1,4 +1,4 @@
-FROM jgehrcke/github-repo-stats-base:f9f4e16c1
+FROM jgehrcke/github-repo-stats-base:e87aa5891
 
 COPY fetch.py /fetch.py
 COPY analyze.py /analyze.py

README.md

@@ -1,8 +1,12 @@
 # github-repo-stats
 
-A GitHub Action ([in Marketplace](https://github.com/marketplace/actions/github-repo-stats)) built to overcome the [14-day limitation](https://github.com/isaacs/github/issues/399) of GitHub's built-in traffic statistics.
+This is a GitHub Action originally built to overcome the [14-day limitation](https://github.com/isaacs/github/issues/399) of GitHub's built-in traffic statistics.
 
-Data that you don't persist today will be gone in two weeks from now.
+Run this daily to collect potentially valuable data.
+
+According to the motto: a data snapshot each day keeps the doctor away 🍎
+
+See [this Action in Marketplace](https://github.com/marketplace/actions/github-repo-stats).
 
 High-level method description:
 
@@ -16,11 +20,13 @@ Looking for a quick start? Follow the [simple tutorial](https://github.com/jgehr
 
 **Demo 1**:
 * [HTML report](https://jgehrcke.github.io/ghrs-test/jgehrcke/github-repo-stats/latest-report/report.html), [PDF report](https://jgehrcke.github.io/ghrs-test/jgehrcke/github-repo-stats/latest-report/report.pdf)
-* [Workflow file](https://github.com/jgehrcke/ghrs-test/blob/github-repo-stats/.github/workflows/github-repo-stats.yml), [data branch](https://github.com/jgehrcke/ghrs-test/tree/github-repo-stats/jgehrcke/github-repo-stats)
+* [Workflow file](https://github.com/jgehrcke/ghrs-test/blob/github-repo-stats/.github/workflows/github-repo-stats-ghrs.yml), [data branch](https://github.com/jgehrcke/ghrs-test/tree/github-repo-stats/jgehrcke/github-repo-stats)
 
 **Demo 2**:
 * [HTML report](https://jgehrcke.github.io/ghrs-test/jgehrcke/covid-19-germany-gae/latest-report/report.html), [PDF report](https://jgehrcke.github.io/ghrs-test/jgehrcke/covid-19-germany-gae/latest-report/report.pdf)
-* [Workflow file](https://github.com/jgehrcke/ghrs-test/blob/covid-19-germany-gae/.github/workflows/github-repo-stats.yml), [data branch](https://github.com/jgehrcke/ghrs-test/tree/covid-19-germany-gae/jgehrcke/github-repo-stats)
+* [Workflow file](https://github.com/jgehrcke/ghrs-test/blob/github-repo-stats/.github/workflows/github-repo-stats-cov19.yml), [data branch](https://github.com/jgehrcke/ghrs-test/tree/github-repo-stats/jgehrcke/github-repo-stats)
+
+For more use cases (and their setup), see "Used by" section below.
 
 ## Highlights
 
@@ -237,10 +243,15 @@ rm -rf .* *; bash /home/jp/dev/github-repo-stats/entrypoint.sh
 
 A few rather randomly picked use cases:
 
+
+* https://github.com/idurar/erp-crm/tree/github-repo-stats/idurar/idurar-erp-crm
+* https://github.com/awslabs/aws-security-analytics-bootstrap/tree/github-repo-stats/awslabs/aws-security-analytics-bootstrap
+* https://github.com/centerofci/mathesar/tree/github-repo-stats/centerofci/mathesar
+* https://github.com/carbon-design-system/carbon/tree/github-repo-stats/carbon-design-system/carbon
+* https://github.com/Pythagora-io/pythagora/tree/github-repo-stats/Pythagora-io/pythagora
 * https://github.com/ignite-hq/cli/tree/github-repo-stats/ignite-hq/cli
 * https://github.com/tom-doerr/github_repo_stats_data/tree/master/tom-doerr
 * https://github.com/ethyca/fides-stats/tree/main/ethyca/fides
 * https://github.com/dylansdaniels/hnn_tracking_test/tree/main/jonescompneurolab/hnn
 * https://github.com/idaholab/repository-statistics/tree/main/idaholab
 * https://github.com/Declipsonator/Tweaks-Stats/tree/main/Declipsonator/Meteor-Tweaks
-* https://github.com/gitsrc/icefiredb-status/tree/github-repo-stats/IceFireDB/IceFireDB

base.Dockerfile

@@ -8,13 +8,13 @@ RUN apt-get update && apt-get install -y -q --no-install-recommends \
         google-chrome-stable \
     && rm -rf /var/lib/apt/lists/*
 
-RUN pip install pip==22.1
+RUN pip install pip==23.2.1
 
 # requirements-fa.txt: dependencies for fetch.py & analyze.py
 # for pdf.py: Note Explore bumping selenium to 4.x
 COPY requirements-fa.txt .
 RUN pip install -r requirements-fa.txt \
-    && pip install selenium==3.141.0 webdriver_manager==3.5.2 #  Dependencies for pdf.py \
+    && pip install selenium==4.13.0 webdriver_manager==4.0.1 #  Dependencies for pdf.py \
     && pip cache purge
 
 RUN echo "biggest dirs"

ci.Dockerfile

@@ -1,4 +1,4 @@
-FROM jgehrcke/github-repo-stats-base:6e6c3e4f8
+FROM jgehrcke/github-repo-stats-base:e87aa5891
 
 # Install GNU parallel
 RUN apt-get update && apt-get install -y -q --no-install-recommends \

pdf.py

@@ -24,6 +24,7 @@
 from selenium import webdriver
 from selenium.webdriver.chrome.options import Options
 from selenium.webdriver.support.ui import WebDriverWait
+from selenium.webdriver.chrome.service import Service
 from webdriver_manager.chrome import ChromeDriverManager
 from selenium.webdriver.common.by import By
 from selenium.webdriver.support.expected_conditions import presence_of_element_located
@@ -78,7 +79,7 @@ def gen_pdf_bytes(html_apath):
     log.info("set up chromedriver with capabilities %s", wd_options.to_capabilities())
 
     with webdriver.Chrome(
-        ChromeDriverManager().install(), options=wd_options
+        service=Service(ChromeDriverManager().install()), options=wd_options
     ) as driver:
         log.info("webdriver set up")
         waiter = WebDriverWait(driver, 10)

requirements-fa.txt

@@ -1,7 +1,7 @@
 # dependencies for fetch.py and analyze.py
-pandas==1.4.2
+pandas==2.1.1
 PyGitHub==1.55
-altair==4.2.0
+altair==4.2.2
 pytz
 retrying
 carbonplan[styles]