diff --git a/.github/workflows/docs-ci.yml b/.github/workflows/docs-ci.yml
index 511b7c2..929abd7 100644
--- a/.github/workflows/docs-ci.yml
+++ b/.github/workflows/docs-ci.yml
@@ -1,10 +1,10 @@
-name: CI Documentation
+name: CI Documentation and Code style
 
 on: [push, pull_request]
 
 jobs:
   build:
-    runs-on: ubuntu-20.04
+    runs-on: ubuntu-22.04
 
     strategy:
       max-parallel: 4
@@ -20,11 +20,8 @@ jobs:
         with:
           python-version: ${{ matrix.python-version }}
 
-      - name: Give permission to run scripts
-        run: chmod +x ./docs/scripts/doc8_style_check.sh
-
       - name: Install Dependencies
-        run:  pip install -e .[docs]
+        run:  pip install -e .[docs,testing]
 
       - name: Check Sphinx Documentation build minimally
         working-directory: ./docs
@@ -34,4 +31,5 @@ jobs:
         working-directory: ./docs
         run: ./scripts/doc8_style_check.sh
 
-
+      - name: Check for Code style errors
+        run: make check-ci
diff --git a/.github/workflows/pypi-release.yml b/.github/workflows/pypi-release.yml
index 9585730..d2206c8 100644
--- a/.github/workflows/pypi-release.yml
+++ b/.github/workflows/pypi-release.yml
@@ -21,10 +21,10 @@ on:
 jobs:
   build-pypi-distribs:
     name: Build and publish library to PyPI
-    runs-on: ubuntu-20.04
+    runs-on: ubuntu-22.04
 
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
       - name: Set up Python
         uses: actions/setup-python@v4
         with:
@@ -47,7 +47,7 @@ jobs:
     name: Create GH release
     needs:
       - build-pypi-distribs
-    runs-on: ubuntu-20.04
+    runs-on: ubuntu-22.04
 
     steps:
       - name: Download built archives
@@ -67,7 +67,7 @@ jobs:
     name: Create PyPI release
     needs:
       - create-gh-release
-    runs-on: ubuntu-20.04
+    runs-on: ubuntu-22.04
 
     steps:
       - name: Download built archives
diff --git a/CHANGELOG.rst b/CHANGELOG.rst
index 2262567..d2e581b 100644
--- a/CHANGELOG.rst
+++ b/CHANGELOG.rst
@@ -1,6 +1,13 @@
 Release notes
 =============
 
+
+Version 32.1.0 - (2024-12-06)
+-----------------------------
+
+- Compute file checksums from streaming the file content in chunks to avoid running out of memory
+
+
 Version 32.0.0 - (2024-09-05)
 -----------------------------
 
diff --git a/Makefile b/Makefile
index cc36c35..9840741 100644
--- a/Makefile
+++ b/Makefile
@@ -4,7 +4,7 @@
 # ScanCode is a trademark of nexB Inc.
 # SPDX-License-Identifier: Apache-2.0
 # See http://www.apache.org/licenses/LICENSE-2.0 for the license text.
-# See https://github.com/nexB/skeleton for support or download.
+# See https://github.com/aboutcode-org/skeleton for support or download.
 # See https://aboutcode.org for more information about nexB OSS projects.
 #
 
@@ -33,11 +33,19 @@ valid: isort black
 
 check:
 	@echo "-> Run pycodestyle (PEP8) validation"
-	@${ACTIVATE} pycodestyle --max-line-length=100 --exclude=.eggs,venv,lib,thirdparty,docs,migrations,settings.py,.cache .
+	@${ACTIVATE} pycodestyle --max-line-length=100 --exclude=.eggs,venv,lib,thirdparty,docs,scripts,tests,migrations,settings.py,.cache .
 	@echo "-> Run isort imports ordering validation"
-	@${ACTIVATE} isort --sl --check-only -l 100 setup.py src tests . 
+	@${ACTIVATE} isort --sl -l 100 src tests setup.py --check-only
 	@echo "-> Run black validation"
-	@${ACTIVATE} black --check --check -l 100 src tests setup.py
+	@${ACTIVATE} black --check -l 100 src tests setup.py
+
+check-ci:
+	@echo "-> Run pycodestyle (PEP8) validation"
+	pycodestyle --max-line-length=100 --exclude=.eggs,venv,lib,thirdparty,docs,scripts,tests,migrations,settings.py,.cache .
+	@echo "-> Run isort imports ordering validation"
+	isort --sl -l 100 src tests setup.py --check-only
+	@echo "-> Run black validation"
+	black --check -l 100 src tests setup.py
 
 clean:
 	@echo "-> Clean the Python env"
diff --git a/azure-pipelines.yml b/azure-pipelines.yml
index d5510e6..9b85823 100644
--- a/azure-pipelines.yml
+++ b/azure-pipelines.yml
@@ -13,7 +13,7 @@ jobs:
     parameters:
       job_name: ubuntu20_cpython
       image_name: ubuntu-20.04
-      python_versions: ["3.8", "3.9", "3.10", "3.11"]
+      python_versions: ["3.9", "3.10", "3.11", "3.12"]
       test_suites:
         all: venv/bin/pytest -n 2 -vvs
 
@@ -21,7 +21,7 @@ jobs:
     parameters:
       job_name: ubuntu22_cpython
       image_name: ubuntu-22.04
-      python_versions: ["3.8", "3.9", "3.10", "3.11"]
+      python_versions: ["3.9", "3.10", "3.11", "3.12"]
       test_suites:
         all: venv/bin/pytest -n 2 -vvs
 
@@ -29,7 +29,7 @@ jobs:
     parameters:
       job_name: macos12_cpython
       image_name: macOS-12
-      python_versions: ["3.8", "3.9", "3.10", "3.11"]
+      python_versions: ["3.9", "3.10", "3.11", "3.12"]
       test_suites:
         all: venv/bin/pytest -n 2 -vvs
 
@@ -37,7 +37,7 @@ jobs:
     parameters:
       job_name: macos13_cpython
       image_name: macOS-13
-      python_versions: ["3.8", "3.9", "3.10", "3.11"]
+      python_versions: ["3.9", "3.10", "3.11", "3.12"]
       test_suites:
         all: venv/bin/pytest -n 2 -vvs
 
@@ -45,7 +45,7 @@ jobs:
     parameters:
       job_name: win2019_cpython
       image_name: windows-2019
-      python_versions: ["3.8", "3.9", "3.10", "3.11"]
+      python_versions: ["3.9", "3.10", "3.11", "3.12"]
       test_suites:
         all: venv\Scripts\pytest -n 2 -vvs
 
@@ -53,7 +53,7 @@ jobs:
     parameters:
       job_name: win2022_cpython
       image_name: windows-2022
-      python_versions: ["3.8", "3.9", "3.10", "3.11"]
+      python_versions: ["3.9", "3.10", "3.11", "3.12"]
       test_suites:
         all: venv\Scripts\pytest -n 2 -vvs
 
@@ -63,9 +63,9 @@ jobs:
 
   - template: etc/ci/azure-posix.yml
     parameters:
-      job_name: ubuntu20_test_all_supported_click_versions
-      image_name: ubuntu-20.04
-      python_versions: ["3.8", "3.9", "3.10", "3.11"]
+      job_name: ubuntu22_test_all_supported_click_versions
+      image_name: ubuntu-22.04
+      python_versions: ["3.9", "3.10", "3.11", "3.12"]
       test_suites:
         click_versions: |
           for clk_ver in 8.1.3 8.1.2 8.1.1 8.1.0 8.0.4 8.0.2 8.0.3 8.0.1 7.1.2 7.1.1 7.1 6.7;
@@ -80,9 +80,9 @@ jobs:
 
   - template: etc/ci/azure-posix.yml
     parameters:
-      job_name: ubuntu20_cpython_latest_from_pip
-      image_name: ubuntu-20.04
-      python_versions: ["3.8", "3.9", "3.10", "3.11"]
+      job_name: ubuntu22_cpython_latest_from_pip
+      image_name: ubuntu-22.04
+      python_versions: ["3.9", "3.10", "3.11", "3.12"]
       test_suites:
         all: |
           venv/bin/pip install --upgrade-strategy eager --force-reinstall --upgrade -e .
@@ -93,7 +93,7 @@ jobs:
     parameters:
       job_name: win2019_cpython_latest_from_pip
       image_name: windows-2019
-      python_versions: ["3.8", "3.9", "3.10", "3.11"]
+      python_versions: ["3.9", "3.10", "3.11", "3.12"]
       test_suites:
         all: |
           venv\Scripts\pip install --upgrade-strategy eager --force-reinstall --upgrade -e .
diff --git a/docs/Makefile b/docs/Makefile
index d0c3cbf..788b039 100644
--- a/docs/Makefile
+++ b/docs/Makefile
@@ -5,6 +5,7 @@
 # from the environment for the first two.
 SPHINXOPTS    ?=
 SPHINXBUILD   ?= sphinx-build
+SPHINXAUTOBUILD = sphinx-autobuild
 SOURCEDIR     = source
 BUILDDIR      = build
 
@@ -14,6 +15,13 @@ help:
 
 .PHONY: help Makefile
 
+# Run the development server using sphinx-autobuild
+docs:
+	@echo
+	@echo "Starting up the docs server..."
+	@echo
+	$(SPHINXAUTOBUILD) --port 8000 --watch ${SOURCEDIR} $(SOURCEDIR) "$(BUILDDIR)/html" $(SPHINXOPTS) $(O)
+
 # Catch-all target: route all unknown targets to Sphinx using the new
 # "make mode" option.  $(O) is meant as a shortcut for $(SPHINXOPTS).
 %: Makefile
diff --git a/docs/make.bat b/docs/make.bat
index 6247f7e..4a3c1a4 100644
--- a/docs/make.bat
+++ b/docs/make.bat
@@ -7,11 +7,16 @@ REM Command file for Sphinx documentation
 if "%SPHINXBUILD%" == "" (
 	set SPHINXBUILD=sphinx-build
 )
+if "%SPHINXAUTOBUILD%" == "" (
+	set SPHINXAUTOBUILD=sphinx-autobuild
+)
 set SOURCEDIR=source
 set BUILDDIR=build
 
 if "%1" == "" goto help
 
+if "%1" == "docs" goto docs
+
 %SPHINXBUILD% >NUL 2>NUL
 if errorlevel 9009 (
 	echo.
@@ -28,6 +33,13 @@ if errorlevel 9009 (
 %SPHINXBUILD% -M %1 %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
 goto end
 
+:docs
+@echo
+@echo Starting up the docs server...
+@echo
+%SPHINXAUTOBUILD% --port 8000 --watch %SOURCEDIR% %SOURCEDIR% %BUILDDIR%\html %SPHINXOPTS% %O%
+goto end
+
 :help
 %SPHINXBUILD% -M help %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
 
diff --git a/docs/scripts/doc8_style_check.sh b/docs/scripts/doc8_style_check.sh
old mode 100644
new mode 100755
diff --git a/docs/source/_static/theme_overrides.css b/docs/source/_static/theme_overrides.css
index 9662d63..5863ccf 100644
--- a/docs/source/_static/theme_overrides.css
+++ b/docs/source/_static/theme_overrides.css
@@ -1,353 +1,26 @@
-body {
-    color: #000000;
-}
-
-p {
-    margin-bottom: 10px;
-}
-
-.wy-plain-list-disc, .rst-content .section ul, .rst-content .toctree-wrapper ul, article ul {
-    margin-bottom: 10px;
-}
-
-.custom_header_01 {
-    color: #cc0000;
-    font-size: 22px;
-    font-weight: bold;
-    line-height: 50px;
-}
-
-h1, h2, h3, h4, h5, h6 {
-    margin-bottom: 20px;
-    margin-top: 20px;
-}
-
-h5 {
-    font-size: 18px;
-    color: #000000;
-    font-style: italic;
-    margin-bottom: 10px;
-}
-
-h6 {
-    font-size: 15px;
-    color: #000000;
-    font-style: italic;
-    margin-bottom: 10px;
-}
-
-/* custom admonitions */
-/* success */
-.custom-admonition-success  .admonition-title {
-    color: #000000;
-    background: #ccffcc;
-    border-radius: 5px 5px 0px 0px;
-}
-div.custom-admonition-success.admonition {
-    color: #000000;
-    background: #ffffff;
-    border: solid 1px #cccccc;
-    border-radius: 5px;
-    box-shadow: 1px 1px 5px 3px #d8d8d8;
-    margin: 20px 0px 30px 0px;
-}
-
-/* important */
-.custom-admonition-important  .admonition-title {
-    color: #000000;
-    background: #ccffcc;
-    border-radius: 5px 5px 0px 0px;
-    border-bottom: solid 1px #000000;
-}
-div.custom-admonition-important.admonition {
-    color: #000000;
-    background: #ffffff;
-    border: solid 1px #cccccc;
-    border-radius: 5px;
-    box-shadow: 1px 1px 5px 3px #d8d8d8;
-    margin: 20px 0px 30px 0px;
-}
-
-/* caution */
-.custom-admonition-caution  .admonition-title {
-    color: #000000;
-    background: #ffff99;
-    border-radius: 5px 5px 0px 0px;
-    border-bottom: solid 1px #e8e8e8;
-}
-div.custom-admonition-caution.admonition {
-    color: #000000;
-    background: #ffffff;
-    border: solid 1px #cccccc;
-    border-radius: 5px;
-    box-shadow: 1px 1px 5px 3px #d8d8d8;
-    margin: 20px 0px 30px 0px;
-}
-
-/* note */
-.custom-admonition-note  .admonition-title {
-    color: #ffffff;
-    background: #006bb3;
-    border-radius: 5px 5px 0px 0px;
-}
-div.custom-admonition-note.admonition {
-    color: #000000;
-    background: #ffffff;
-    border: solid 1px #cccccc;
-    border-radius: 5px;
-    box-shadow: 1px 1px 5px 3px #d8d8d8;
-    margin: 20px 0px 30px 0px;
-}
-
-/* todo */
-.custom-admonition-todo  .admonition-title {
-    color: #000000;
-    background: #cce6ff;
-    border-radius: 5px 5px 0px 0px;
-    border-bottom: solid 1px #99ccff;
-}
-div.custom-admonition-todo.admonition {
-    color: #000000;
-    background: #ffffff;
-    border: solid 1px #99ccff;
-    border-radius: 5px;
-    box-shadow: 1px 1px 5px 3px #d8d8d8;
-    margin: 20px 0px 30px 0px;
-}
-
-/* examples */
-.custom-admonition-examples  .admonition-title {
-    color: #000000;
-    background: #ffe6cc;
-    border-radius: 5px 5px 0px 0px;
-    border-bottom: solid 1px #d8d8d8;
-}
-div.custom-admonition-examples.admonition {
-    color: #000000;
-    background: #ffffff;
-    border: solid 1px #cccccc;
-    border-radius: 5px;
-    box-shadow: 1px 1px 5px 3px #d8d8d8;
-    margin: 20px 0px 30px 0px;
-}
-
+/* this is the container for the pages */
 .wy-nav-content {
     max-width: 100%;
-    padding-right: 100px;
-    padding-left: 100px;
-    background-color: #f2f2f2;
-}
-
-div.rst-content {
-    background-color: #ffffff;
-    border: solid 1px #e5e5e5;
-    padding: 20px 40px 20px 40px;
-}
-
-.rst-content .guilabel {
-    border: 1px solid #ffff99;
-    background: #ffff99;
-    font-size: 100%;
-    font-weight: normal;
-    border-radius: 4px;
-    padding: 2px 0px;
-    margin: auto 2px;
-    vertical-align: middle;
-}
-
-.rst-content kbd {
-    font-family: SFMono-Regular,Menlo,Monaco,Consolas,"Liberation Mono","Courier New",Courier,monospace;
-    border: solid 1px #d8d8d8;
-    background-color: #f5f5f5;
-    padding: 0px 3px;
-    border-radius: 3px;
-}
-
-.wy-nav-content-wrap a {
-    color: #0066cc;
-    text-decoration: none;
-}
-.wy-nav-content-wrap a:hover {
-    color: #0099cc;
-    text-decoration: underline;
-}
-
-.wy-nav-top a {
-    color: #ffffff;
-}
-
-/* Based on numerous similar approaches e.g., https://github.com/readthedocs/sphinx_rtd_theme/issues/117 and https://rackerlabs.github.io/docs-rackspace/tools/rtd-tables.html -- but remove form-factor limits to enable table wrap on full-size and smallest-size form factors */
-.wy-table-responsive table td {
-    white-space: normal !important;
-}
-
-.rst-content table.docutils td,
-.rst-content table.docutils th {
-    padding: 5px 10px 5px 10px;
-}
-.rst-content table.docutils td p,
-.rst-content table.docutils th p {
-    font-size: 14px;
-    margin-bottom: 0px;
-}
-.rst-content table.docutils td p cite,
-.rst-content table.docutils th p cite {
-    font-size: 14px;
-    background-color: transparent;
-}
-
-.colwidths-given th {
-    border: solid 1px #d8d8d8 !important;
-}
-.colwidths-given td {
-    border: solid 1px #d8d8d8 !important;
-}
-
-/*handles single-tick inline code*/
-.wy-body-for-nav cite {
-    color: #000000;
-    background-color: transparent;
-    font-style: normal;
-    font-family: "Courier New";
-    font-size: 13px;
-    padding: 3px 3px 3px 3px;
-}
-
-.rst-content pre.literal-block, .rst-content div[class^="highlight"] pre, .rst-content .linenodiv pre {
-    font-family: SFMono-Regular,Menlo,Monaco,Consolas,"Liberation Mono","Courier New",Courier,monospace;
-    font-size: 13px;
-    overflow: visible;
-    white-space: pre-wrap;
-    color: #000000;
-}
-
-.rst-content pre.literal-block, .rst-content div[class^='highlight'] {
-    background-color: #f8f8f8;
-    border: solid 1px #e8e8e8;
-}
-
-/* This enables inline code to wrap. */
-code, .rst-content tt, .rst-content code {
-    white-space: pre-wrap;
-    padding: 2px 3px 1px;
-    border-radius: 3px;
-    font-size: 13px;
-    background-color: #ffffff;
-}
-
-/* use this added class for code blocks attached to bulleted list items */
-.highlight-top-margin {
-    margin-top: 20px !important;
-}
-
-/* change color of inline code block */
-span.pre {
-    color: #e01e5a;
-}
-
-.wy-body-for-nav blockquote {
-    margin: 1em 0;
-    padding-left: 1em;
-    border-left: 4px solid #ddd;
-    color: #000000;
-}
-
-/* Fix the unwanted top and bottom padding inside a nested bulleted/numbered list */
-.rst-content .section ol p, .rst-content .section ul p {
-    margin-bottom: 0px;
-}
-
-/* add spacing between bullets for legibility */
-.rst-content .section ol li, .rst-content .section ul li {
-    margin-bottom: 5px;
-}
-
-.rst-content .section ol li:first-child, .rst-content .section ul li:first-child {
-    margin-top: 5px;
-}
-
-/* but exclude the toctree bullets */
-.rst-content .toctree-wrapper ul li, .rst-content .toctree-wrapper ul li:first-child {
+    padding: 0px 40px 0px 0px;
     margin-top: 0px;
-    margin-bottom: 0px;
 }
 
-/* remove extra space at bottom of multine list-table cell */
-.rst-content .line-block {
-    margin-left: 0px;
-    margin-bottom: 0px;
-    line-height: 24px;
+.wy-nav-content-wrap {
+    border-right: solid 1px;
 }
 
-/* fix extra vertical spacing in page toctree */
-.rst-content .toctree-wrapper ul li ul, article ul li ul {
-    margin-top: 0;
-    margin-bottom: 0;
-}
-
-/* this is used by the genindex added via layout.html (see source/_templates/) to sidebar toc */
-.reference.internal.toc-index {
-    color: #d9d9d9;
-}
-
-.reference.internal.toc-index.current {
-    background-color: #ffffff;
-    color: #000000;
-    font-weight: bold;
-}
-
-.toc-index-div {
-    border-top: solid 1px #000000;
-    margin-top: 10px;
-    padding-top: 5px;
-}
-
-.indextable ul li {
-    font-size: 14px;
-    margin-bottom: 5px;
-}
-
-/* The next 2 fix the poor vertical spacing in genindex.html (the alphabetized index) */
-.indextable.genindextable {
-    margin-bottom: 20px;
-}
-
-div.genindex-jumpbox {
-    margin-bottom: 10px;
-}
-
-/* rst image classes */
-
-.clear-both {
-    clear: both;
-  }
-
-.float-left {
-    float: left;
-    margin-right: 20px;
-}
-
-img {
-    border: solid 1px #e8e8e8;
-}
-
-/* These are custom and need to be defined in conf.py to access in all pages, e.g., '.. role:: red' */
-.img-title {
-    color: #000000;
-    /* neither padding nor margin works for vertical spacing bc it's a span -- line-height does, sort of */
-    line-height: 3.0;
-    font-style: italic;
-    font-weight: 600;
-}
-
-.img-title-para {
-    color: #000000;
-    margin-top: 20px;
-    margin-bottom: 0px;
-    font-style: italic;
-    font-weight: 500;
-}
-
-.red {
-    color: red;
+div.rst-content {
+    max-width: 1300px;
+    border: 0;
+    padding: 10px 80px 10px 80px;
+    margin-left: 50px;
+}
+
+@media (max-width: 768px) {
+    div.rst-content {
+        max-width: 1300px;
+        border: 0;
+        padding: 0px 10px 10px 10px;
+        margin-left: 0px;
+    }
 }
diff --git a/docs/source/conf.py b/docs/source/conf.py
index 918d62c..8c88fa2 100644
--- a/docs/source/conf.py
+++ b/docs/source/conf.py
@@ -30,6 +30,10 @@
 extensions = [
     "sphinx.ext.intersphinx",
     "sphinx_reredirects",
+    "sphinx_rtd_theme",
+    "sphinx_rtd_dark_mode",
+    "sphinx.ext.extlinks",
+    "sphinx_copybutton",
 ]
 
 
@@ -39,11 +43,14 @@
 
 # This points to aboutcode.readthedocs.io
 # In case of "undefined label" ERRORS check docs on intersphinx to troubleshoot
-# Link was created at commit - https://github.com/nexB/aboutcode/commit/faea9fcf3248f8f198844fe34d43833224ac4a83
+# Link was created at commit - https://github.com/aboutcode-org/aboutcode/commit/faea9fcf3248f8f198844fe34d43833224ac4a83
 
 intersphinx_mapping = {
     "aboutcode": ("https://aboutcode.readthedocs.io/en/latest/", None),
-    "scancode-workbench": ("https://scancode-workbench.readthedocs.io/en/develop/", None),
+    "scancode-workbench": (
+        "https://scancode-workbench.readthedocs.io/en/develop/",
+        None,
+    ),
 }
 
 
@@ -78,7 +85,9 @@
     "conf_py_path": "/docs/source/",  # path in the checkout to the docs root
 }
 
-html_css_files = ["_static/theme_overrides.css"]
+html_css_files = [
+    "theme_overrides.css",
+]
 
 
 # If true, "Created using Sphinx" is shown in the HTML footer. Default is True.
@@ -104,6 +113,4 @@
 
 # -- Options for LaTeX output -------------------------------------------------
 
-latex_elements = {
-    'classoptions': ',openany,oneside'
-}
\ No newline at end of file
+latex_elements = {"classoptions": ",openany,oneside"}
diff --git a/docs/source/contribute/contrib_doc.rst b/docs/source/contribute/contrib_doc.rst
index 13882e1..5640db2 100644
--- a/docs/source/contribute/contrib_doc.rst
+++ b/docs/source/contribute/contrib_doc.rst
@@ -12,7 +12,7 @@ To get started, create or identify a working directory on your local machine.
 
 Open that directory and execute the following command in a terminal session::
 
-    git clone https://github.com/nexB/skeleton.git
+    git clone https://github.com/aboutcode-org/skeleton.git
 
 That will create an ``/skeleton`` directory in your working directory.
 Now you can install the dependencies in a virtualenv::
diff --git a/etc/scripts/check_thirdparty.py b/etc/scripts/check_thirdparty.py
index b052f25..2daded9 100644
--- a/etc/scripts/check_thirdparty.py
+++ b/etc/scripts/check_thirdparty.py
@@ -5,7 +5,7 @@
 # ScanCode is a trademark of nexB Inc.
 # SPDX-License-Identifier: Apache-2.0
 # See http://www.apache.org/licenses/LICENSE-2.0 for the license text.
-# See https://github.com/nexB/skeleton for support or download.
+# See https://github.com/aboutcode-org/skeleton for support or download.
 # See https://aboutcode.org for more information about nexB OSS projects.
 #
 import click
@@ -17,7 +17,8 @@
 @click.option(
     "-d",
     "--dest",
-    type=click.Path(exists=True, readable=True, path_type=str, file_okay=False),
+    type=click.Path(exists=True, readable=True,
+                    path_type=str, file_okay=False),
     required=True,
     help="Path to the thirdparty directory to check.",
 )
diff --git a/etc/scripts/fetch_thirdparty.py b/etc/scripts/fetch_thirdparty.py
index eedf05c..3f9ff52 100644
--- a/etc/scripts/fetch_thirdparty.py
+++ b/etc/scripts/fetch_thirdparty.py
@@ -5,7 +5,7 @@
 # ScanCode is a trademark of nexB Inc.
 # SPDX-License-Identifier: Apache-2.0
 # See http://www.apache.org/licenses/LICENSE-2.0 for the license text.
-# See https://github.com/nexB/skeleton for support or download.
+# See https://github.com/aboutcode-org/skeleton for support or download.
 # See https://aboutcode.org for more information about nexB OSS projects.
 #
 
@@ -55,7 +55,8 @@
     "-d",
     "--dest",
     "dest_dir",
-    type=click.Path(exists=True, readable=True, path_type=str, file_okay=False),
+    type=click.Path(exists=True, readable=True,
+                    path_type=str, file_okay=False),
     metavar="DIR",
     default=utils_thirdparty.THIRDPARTY_DIR,
     show_default=True,
@@ -224,7 +225,8 @@ def fetch_thirdparty(
     environments = None
     if wheels:
         evts = itertools.product(python_versions, operating_systems)
-        environments = [utils_thirdparty.Environment.from_pyver_and_os(pyv, os) for pyv, os in evts]
+        environments = [utils_thirdparty.Environment.from_pyver_and_os(
+            pyv, os) for pyv, os in evts]
 
     # Collect PyPI repos
     repos = []
@@ -260,13 +262,14 @@ def fetch_thirdparty(
                     repos=repos,
                 )
                 if not fetched:
-                    wheels_or_sdist_not_found[f"{name}=={version}"].append(environment)
+                    wheels_or_sdist_not_found[f"{name}=={version}"].append(
+                        environment)
                     if TRACE:
                         print(f"      NOT FOUND")
 
         if (sdists or
             (f"{name}=={version}" in wheels_or_sdist_not_found and name in sdist_only)
-         ):
+            ):
             if TRACE:
                 print(f"  ==> Fetching sdist: {name}=={version}")
 
@@ -289,7 +292,8 @@ def fetch_thirdparty(
         sdist_missing = sdists and "sdist" in dists and not name in wheel_only
         if sdist_missing:
             mia.append(f"SDist missing: {nv} {dists}")
-        wheels_missing = wheels and any(d for d in dists if d != "sdist") and not name in sdist_only
+        wheels_missing = wheels and any(
+            d for d in dists if d != "sdist") and not name in sdist_only
         if wheels_missing:
             mia.append(f"Wheels missing: {nv} {dists}")
 
@@ -299,7 +303,8 @@ def fetch_thirdparty(
         raise Exception(mia)
 
     print(f"==> FETCHING OR CREATING ABOUT AND LICENSE FILES")
-    utils_thirdparty.fetch_abouts_and_licenses(dest_dir=dest_dir, use_cached_index=use_cached_index)
+    utils_thirdparty.fetch_abouts_and_licenses(
+        dest_dir=dest_dir, use_cached_index=use_cached_index)
     utils_thirdparty.clean_about_files(dest_dir=dest_dir)
 
     # check for problems
diff --git a/etc/scripts/gen_requirements.py b/etc/scripts/gen_requirements.py
index 07e26f7..2b65ae8 100644
--- a/etc/scripts/gen_requirements.py
+++ b/etc/scripts/gen_requirements.py
@@ -5,7 +5,7 @@
 # ScanCode is a trademark of nexB Inc.
 # SPDX-License-Identifier: Apache-2.0
 # See http://www.apache.org/licenses/LICENSE-2.0 for the license text.
-# See https://github.com/nexB/skeleton for support or download.
+# See https://github.com/aboutcode-org/skeleton for support or download.
 # See https://aboutcode.org for more information about nexB OSS projects.
 #
 import argparse
diff --git a/etc/scripts/gen_requirements_dev.py b/etc/scripts/gen_requirements_dev.py
index 12cc06d..5db1c48 100644
--- a/etc/scripts/gen_requirements_dev.py
+++ b/etc/scripts/gen_requirements_dev.py
@@ -5,7 +5,7 @@
 # ScanCode is a trademark of nexB Inc.
 # SPDX-License-Identifier: Apache-2.0
 # See http://www.apache.org/licenses/LICENSE-2.0 for the license text.
-# See https://github.com/nexB/skeleton for support or download.
+# See https://github.com/aboutcode-org/skeleton for support or download.
 # See https://aboutcode.org for more information about nexB OSS projects.
 #
 import argparse
diff --git a/etc/scripts/utils_dejacode.py b/etc/scripts/utils_dejacode.py
index c42e6c9..652252d 100644
--- a/etc/scripts/utils_dejacode.py
+++ b/etc/scripts/utils_dejacode.py
@@ -5,7 +5,7 @@
 # ScanCode is a trademark of nexB Inc.
 # SPDX-License-Identifier: Apache-2.0
 # See http://www.apache.org/licenses/LICENSE-2.0 for the license text.
-# See https://github.com/nexB/skeleton for support or download.
+# See https://github.com/aboutcode-org/skeleton for support or download.
 # See https://aboutcode.org for more information about nexB OSS projects.
 #
 import io
@@ -33,7 +33,8 @@
 
 def can_do_api_calls():
     if not DEJACODE_API_KEY and DEJACODE_API_URL:
-        print("DejaCode DEJACODE_API_KEY and DEJACODE_API_URL not configured. Doing nothing")
+        print(
+            "DejaCode DEJACODE_API_KEY and DEJACODE_API_URL not configured. Doing nothing")
         return False
     else:
         return True
@@ -68,7 +69,8 @@ def get_package_data(distribution):
         return results[0]
 
     elif len_results > 1:
-        print(f"More than 1 entry exists, review at: {DEJACODE_API_URL_PACKAGES}")
+        print(
+            f"More than 1 entry exists, review at: {DEJACODE_API_URL_PACKAGES}")
     else:
         print("Could not find package:", distribution.download_url)
 
@@ -149,7 +151,8 @@ def find_latest_dejacode_package(distribution):
     # there was no exact match, find the latest version
     # TODO: consider the closest version rather than the latest
     # or the version that has the best data
-    with_versions = [(packaging_version.parse(p["version"]), p) for p in packages]
+    with_versions = [(packaging_version.parse(p["version"]), p)
+                     for p in packages]
     with_versions = sorted(with_versions)
     latest_version, latest_package_version = sorted(with_versions)[-1]
     print(
diff --git a/etc/scripts/utils_requirements.py b/etc/scripts/utils_requirements.py
index 0fc25a3..1c50239 100644
--- a/etc/scripts/utils_requirements.py
+++ b/etc/scripts/utils_requirements.py
@@ -5,7 +5,7 @@
 # ScanCode is a trademark of nexB Inc.
 # SPDX-License-Identifier: Apache-2.0
 # See http://www.apache.org/licenses/LICENSE-2.0 for the license text.
-# See https://github.com/nexB/skeleton for support or download.
+# See https://github.com/aboutcode-org/skeleton for support or download.
 # See https://aboutcode.org for more information about nexB OSS projects.
 #
 
@@ -102,7 +102,8 @@ def lock_dev_requirements(
     all_req_nvs = get_required_name_versions(all_req_lines)
     dev_only_req_nvs = {n: v for n, v in all_req_nvs if n not in main_names}
 
-    new_reqs = "\n".join(f"{n}=={v}" for n, v in sorted(dev_only_req_nvs.items()))
+    new_reqs = "\n".join(
+        f"{n}=={v}" for n, v in sorted(dev_only_req_nvs.items()))
     with open(dev_requirements_file, "w") as fo:
         fo.write(new_reqs)
 
@@ -113,10 +114,12 @@ def get_installed_reqs(site_packages_dir):
     as a text.
     """
     if not os.path.exists(site_packages_dir):
-        raise Exception(f"site_packages directory: {site_packages_dir!r} does not exists")
+        raise Exception(
+            f"site_packages directory: {site_packages_dir!r} does not exists")
     # Also include these packages in the output with --all: wheel, distribute,
     # setuptools, pip
-    args = ["pip", "freeze", "--exclude-editable", "--all", "--path", site_packages_dir]
+    args = ["pip", "freeze", "--exclude-editable",
+            "--all", "--path", site_packages_dir]
     return subprocess.check_output(args, encoding="utf-8")
 
 
diff --git a/etc/scripts/utils_thirdparty.py b/etc/scripts/utils_thirdparty.py
index addf8e5..569b605 100644
--- a/etc/scripts/utils_thirdparty.py
+++ b/etc/scripts/utils_thirdparty.py
@@ -5,7 +5,7 @@
 # ScanCode is a trademark of nexB Inc.
 # SPDX-License-Identifier: Apache-2.0
 # See http://www.apache.org/licenses/LICENSE-2.0 for the license text.
-# See https://github.com/nexB/skeleton for support or download.
+# See https://github.com/aboutcode-org/skeleton for support or download.
 # See https://aboutcode.org for more information about nexB OSS projects.
 #
 import email
@@ -245,9 +245,11 @@ def download_wheel(name, version, environment, dest_dir=THIRDPARTY_DIR, repos=tu
         package = repo.get_package_version(name=name, version=version)
         if not package:
             if TRACE_DEEP:
-                print(f"    download_wheel: No package in {repo.index_url} for {name}=={version}")
+                print(
+                    f"    download_wheel: No package in {repo.index_url} for {name}=={version}")
             continue
-        supported_wheels = list(package.get_supported_wheels(environment=environment))
+        supported_wheels = list(
+            package.get_supported_wheels(environment=environment))
         if not supported_wheels:
             if TRACE_DEEP:
                 print(
@@ -291,7 +293,8 @@ def download_sdist(name, version, dest_dir=THIRDPARTY_DIR, repos=tuple()):
 
         if not package:
             if TRACE_DEEP:
-                print(f"    download_sdist: No package in {repo.index_url} for {name}=={version}")
+                print(
+                    f"    download_sdist: No package in {repo.index_url} for {name}=={version}")
             continue
         sdist = package.sdist
         if not sdist:
@@ -300,7 +303,8 @@ def download_sdist(name, version, dest_dir=THIRDPARTY_DIR, repos=tuple()):
             continue
 
         if TRACE_DEEP:
-            print(f"    download_sdist: Getting sdist from index (or cache): {sdist.download_url}")
+            print(
+                f"    download_sdist: Getting sdist from index (or cache): {sdist.download_url}")
         fetched_sdist_filename = package.sdist.download(dest_dir=dest_dir)
 
         if fetched_sdist_filename:
@@ -533,7 +537,8 @@ def get_best_download_url(self, repos=tuple()):
             repos = DEFAULT_PYPI_REPOS
 
         for repo in repos:
-            package = repo.get_package_version(name=self.name, version=self.version)
+            package = repo.get_package_version(
+                name=self.name, version=self.version)
             if not package:
                 if TRACE:
                     print(
@@ -772,7 +777,8 @@ def load_remote_about_data(self):
                 if notice_text:
                     about_data["notice_text"] = notice_text
             except RemoteNotFetchedException:
-                print(f"Failed to fetch NOTICE file: {self.notice_download_url}")
+                print(
+                    f"Failed to fetch NOTICE file: {self.notice_download_url}")
         return self.load_about_data(about_data)
 
     def get_checksums(self, dest_dir=THIRDPARTY_DIR):
@@ -821,9 +827,11 @@ def fetch_license_files(self, dest_dir=THIRDPARTY_DIR, use_cached_index=False):
         Fetch license files if missing in `dest_dir`.
         Return True if license files were fetched.
         """
-        urls = LinksRepository.from_url(use_cached_index=use_cached_index).links
+        urls = LinksRepository.from_url(
+            use_cached_index=use_cached_index).links
         errors = []
-        extra_lic_names = [l.get("file") for l in self.extra_data.get("licenses", {})]
+        extra_lic_names = [l.get("file")
+                           for l in self.extra_data.get("licenses", {})]
         extra_lic_names += [self.extra_data.get("license_file")]
         extra_lic_names = [ln for ln in extra_lic_names if ln]
         lic_names = [f"{key}.LICENSE" for key in self.get_license_keys()]
@@ -834,7 +842,8 @@ def fetch_license_files(self, dest_dir=THIRDPARTY_DIR, use_cached_index=False):
 
             try:
                 # try remotely first
-                lic_url = get_license_link_for_filename(filename=filename, urls=urls)
+                lic_url = get_license_link_for_filename(
+                    filename=filename, urls=urls)
 
                 fetch_and_save(
                     path_or_url=lic_url,
@@ -845,7 +854,7 @@ def fetch_license_files(self, dest_dir=THIRDPARTY_DIR, use_cached_index=False):
                 if TRACE:
                     print(f"Fetched license from remote: {lic_url}")
 
-            except:
+            except Exception:
                 try:
                     # try licensedb second
                     lic_url = f"{LICENSEDB_API_URL}/{filename}"
@@ -858,7 +867,7 @@ def fetch_license_files(self, dest_dir=THIRDPARTY_DIR, use_cached_index=False):
                     if TRACE:
                         print(f"Fetched license from licensedb: {lic_url}")
 
-                except:
+                except Exception:
                     msg = f'No text for license {filename} in expression "{self.license_expression}" from {self}'
                     print(msg)
                     errors.append(msg)
@@ -911,7 +920,8 @@ def load_pkginfo_data(self, dest_dir=THIRDPARTY_DIR):
             c for c in classifiers if c.startswith("License")
         ]
         license_expression = get_license_expression(declared_license)
-        other_classifiers = [c for c in classifiers if not c.startswith("License")]
+        other_classifiers = [
+            c for c in classifiers if not c.startswith("License")]
 
         holder = raw_data["Author"]
         holder_contact = raw_data["Author-email"]
@@ -953,7 +963,8 @@ def update(self, data, overwrite=False, keep_extra=True):
         package_url = data.get("package_url")
         if package_url:
             purl_from_data = packageurl.PackageURL.from_string(package_url)
-            purl_from_self = packageurl.PackageURL.from_string(self.package_url)
+            purl_from_self = packageurl.PackageURL.from_string(
+                self.package_url)
             if purl_from_data != purl_from_self:
                 print(
                     f"Invalid dist update attempt, no same same purl with dist: "
@@ -1003,7 +1014,8 @@ def get_license_link_for_filename(filename, urls):
     if not path_or_url:
         raise Exception(f"Missing link to file: {filename}")
     if not len(path_or_url) == 1:
-        raise Exception(f"Multiple links to file: {filename}: \n" + "\n".join(path_or_url))
+        raise Exception(
+            f"Multiple links to file: {filename}: \n" + "\n".join(path_or_url))
     return path_or_url[0]
 
 
@@ -1290,7 +1302,7 @@ def is_pure(self):
 def is_pure_wheel(filename):
     try:
         return Wheel.from_filename(filename).is_pure()
-    except:
+    except Exception:
         return False
 
 
@@ -1397,7 +1409,8 @@ def packages_from_dir(cls, directory):
         """
         base = os.path.abspath(directory)
 
-        paths = [os.path.join(base, f) for f in os.listdir(base) if f.endswith(EXTENSIONS)]
+        paths = [os.path.join(base, f)
+                 for f in os.listdir(base) if f.endswith(EXTENSIONS)]
 
         if TRACE_ULTRA_DEEP:
             print("packages_from_dir: paths:", paths)
@@ -1458,7 +1471,8 @@ def dists_from_paths_or_urls(cls, paths_or_urls):
         dists = []
         if TRACE_ULTRA_DEEP:
             print("     ###paths_or_urls:", paths_or_urls)
-        installable = [f for f in paths_or_urls if f.endswith(EXTENSIONS_INSTALLABLE)]
+        installable = [f for f in paths_or_urls if f.endswith(
+            EXTENSIONS_INSTALLABLE)]
         for path_or_url in installable:
             try:
                 dist = Distribution.from_path_or_url(path_or_url)
@@ -1476,7 +1490,8 @@ def dists_from_paths_or_urls(cls, paths_or_urls):
                     )
             except InvalidDistributionFilename:
                 if TRACE_DEEP:
-                    print(f"     Skipping invalid distribution from: {path_or_url}")
+                    print(
+                        f"     Skipping invalid distribution from: {path_or_url}")
                 continue
         return dists
 
@@ -1525,7 +1540,8 @@ class Environment:
     implementation = attr.ib(
         type=str,
         default="cp",
-        metadata=dict(help="Python implementation supported by this environment."),
+        metadata=dict(
+            help="Python implementation supported by this environment."),
         repr=False,
     )
 
@@ -1539,7 +1555,8 @@ class Environment:
     platforms = attr.ib(
         type=list,
         default=attr.Factory(list),
-        metadata=dict(help="List of platform tags supported by this environment."),
+        metadata=dict(
+            help="List of platform tags supported by this environment."),
         repr=False,
     )
 
@@ -1623,7 +1640,8 @@ class PypiSimpleRepository:
     fetched_package_normalized_names = attr.ib(
         type=set,
         default=attr.Factory(set),
-        metadata=dict(help="A set of already fetched package normalized names."),
+        metadata=dict(
+            help="A set of already fetched package normalized names."),
     )
 
     use_cached_index = attr.ib(
@@ -1654,10 +1672,12 @@ def _get_package_versions_map(self, name):
                 self.packages[normalized_name] = versions
             except RemoteNotFetchedException as e:
                 if TRACE:
-                    print(f"failed to fetch package name: {name} from: {self.index_url}:\n{e}")
+                    print(
+                        f"failed to fetch package name: {name} from: {self.index_url}:\n{e}")
 
         if not versions and TRACE:
-            print(f"WARNING: package {name} not found in repo: {self.index_url}")
+            print(
+                f"WARNING: package {name} not found in repo: {self.index_url}")
 
         return versions
 
@@ -1842,7 +1862,8 @@ def get(self, path_or_url, as_text=True, force=False):
         if force or not os.path.exists(cached):
             if TRACE_DEEP:
                 print(f"        FILE CACHE MISS: {path_or_url}")
-            content = get_file_content(path_or_url=path_or_url, as_text=as_text)
+            content = get_file_content(
+                path_or_url=path_or_url, as_text=as_text)
             wmode = "w" if as_text else "wb"
             with open(cached, wmode) as fo:
                 fo.write(content)
@@ -1864,7 +1885,8 @@ def get_file_content(path_or_url, as_text=True):
     if path_or_url.startswith("https://"):
         if TRACE_DEEP:
             print(f"Fetching: {path_or_url}")
-        _headers, content = get_remote_file_content(url=path_or_url, as_text=as_text)
+        _headers, content = get_remote_file_content(
+            url=path_or_url, as_text=as_text)
         return content
 
     elif path_or_url.startswith("file://") or (
@@ -1930,7 +1952,8 @@ def get_remote_file_content(
                 )
 
             else:
-                raise RemoteNotFetchedException(f"Failed HTTP request from {url} with {status}")
+                raise RemoteNotFetchedException(
+                    f"Failed HTTP request from {url} with {status}")
 
         if headers_only:
             return response.headers, None
@@ -2021,7 +2044,8 @@ def get_other_dists(_package, _dist):
             # if has key data we may look to improve later, but we can move on
             if local_dist.has_key_metadata():
                 local_dist.save_about_and_notice_files(dest_dir=dest_dir)
-                local_dist.fetch_license_files(dest_dir=dest_dir, use_cached_index=use_cached_index)
+                local_dist.fetch_license_files(
+                    dest_dir=dest_dir, use_cached_index=use_cached_index)
                 continue
 
             # lets try to get from another dist of the same local package
@@ -2033,7 +2057,8 @@ def get_other_dists(_package, _dist):
             # if has key data we may look to improve later, but we can move on
             if local_dist.has_key_metadata():
                 local_dist.save_about_and_notice_files(dest_dir=dest_dir)
-                local_dist.fetch_license_files(dest_dir=dest_dir, use_cached_index=use_cached_index)
+                local_dist.fetch_license_files(
+                    dest_dir=dest_dir, use_cached_index=use_cached_index)
                 continue
 
             # try to get another version of the same package that is not our version
@@ -2044,7 +2069,8 @@ def get_other_dists(_package, _dist):
             ]
             other_local_version = other_local_packages and other_local_packages[-1]
             if other_local_version:
-                latest_local_dists = list(other_local_version.get_distributions())
+                latest_local_dists = list(
+                    other_local_version.get_distributions())
                 for latest_local_dist in latest_local_dists:
                     latest_local_dist.load_about_data(dest_dir=dest_dir)
                     if not latest_local_dist.has_key_metadata():
@@ -2070,7 +2096,8 @@ def get_other_dists(_package, _dist):
             # if has key data we may look to improve later, but we can move on
             if local_dist.has_key_metadata():
                 local_dist.save_about_and_notice_files(dest_dir=dest_dir)
-                local_dist.fetch_license_files(dest_dir=dest_dir, use_cached_index=use_cached_index)
+                local_dist.fetch_license_files(
+                    dest_dir=dest_dir, use_cached_index=use_cached_index)
                 continue
 
             # try to get a latest version of the same package that is not our version
@@ -2111,7 +2138,8 @@ def get_other_dists(_package, _dist):
             # if local_dist.has_key_metadata() or not local_dist.has_key_metadata():
             local_dist.save_about_and_notice_files(dest_dir)
 
-            lic_errs = local_dist.fetch_license_files(dest_dir, use_cached_index=use_cached_index)
+            lic_errs = local_dist.fetch_license_files(
+                dest_dir, use_cached_index=use_cached_index)
 
             if not local_dist.has_key_metadata():
                 print(f"Unable to add essential ABOUT data for: {local_dist}")
@@ -2259,7 +2287,8 @@ def find_problems(
 
         for dist in package.get_distributions():
             dist.load_about_data(dest_dir=dest_dir)
-            abpth = os.path.abspath(os.path.join(dest_dir, dist.about_filename))
+            abpth = os.path.abspath(os.path.join(
+                dest_dir, dist.about_filename))
             if not dist.has_key_metadata():
                 print(f"   Missing key ABOUT data in file://{abpth}")
             if "classifiers" in dist.extra_data:
diff --git a/setup.cfg b/setup.cfg
index 163d21b..353b78f 100644
--- a/setup.cfg
+++ b/setup.cfg
@@ -37,7 +37,7 @@ zip_safe = false
 
 setup_requires = setuptools_scm[toml] >= 4
 
-python_requires = >=3.8
+python_requires = >=3.9
 
 install_requires =
     attrs >= 18.1, !=20.1.0
@@ -67,4 +67,7 @@ docs =
     sphinx-rtd-theme>=1.0.0
     sphinx-reredirects >= 0.1.2
     doc8>=0.11.2
+    sphinx-autobuild
+    sphinx-rtd-dark-mode>=1.3.0
+    sphinx-copybutton
 
diff --git a/src/commoncode/cliutils.py b/src/commoncode/cliutils.py
index 1638088..8ec419c 100644
--- a/src/commoncode/cliutils.py
+++ b/src/commoncode/cliutils.py
@@ -10,9 +10,7 @@
 import sys
 
 import click
-
-# FIXME: this is NOT API
-from click._termui_impl import ProgressBar
+from click._termui_impl import ProgressBar  # FIXME: this is NOT API
 from click.termui import style
 from click.types import BoolParamType
 from click.utils import echo
diff --git a/src/commoncode/command.py b/src/commoncode/command.py
index 2570a05..419da26 100644
--- a/src/commoncode/command.py
+++ b/src/commoncode/command.py
@@ -203,7 +203,7 @@ def close_pipe(p):
         # Ensure process death otherwise proc.wait may hang in some cases
         # NB: this will run only on POSIX OSes supporting signals
         os.kill(proc.pid, signal.SIGKILL)  # NOQA
-    except:
+    except Exception:
         pass
 
     # This may slow things down a tad on non-POSIX Oses but is safe:
diff --git a/src/commoncode/fileset.py b/src/commoncode/fileset.py
index 9ebab26..f0298ea 100644
--- a/src/commoncode/fileset.py
+++ b/src/commoncode/fileset.py
@@ -161,7 +161,7 @@ def load(location):
     assert os.path.exists(fn) and os.path.isfile(fn), msg
     mode = "r"
     with open(fn, mode) as f:
-        return [l.strip() for l in f if l and l.strip()]
+        return [line.strip() for line in f if line and line.strip()]
 
 
 def includes_excludes(patterns, message):
diff --git a/src/commoncode/fileutils.py b/src/commoncode/fileutils.py
index 123a717..3f6f9ec 100644
--- a/src/commoncode/fileutils.py
+++ b/src/commoncode/fileutils.py
@@ -557,7 +557,7 @@ def _rm_handler(function, path, excinfo):  # NOQA
     elif function == os.remove:
         try:
             delete(path, _err_handler=None)
-        except:
+        except Exception:
             pass
 
         if os.path.exists(path):
diff --git a/src/commoncode/hash.py b/src/commoncode/hash.py
index 954d3f4..5e71fde 100644
--- a/src/commoncode/hash.py
+++ b/src/commoncode/hash.py
@@ -8,6 +8,7 @@
 
 import binascii
 import hashlib
+import os
 import sys
 from functools import partial
 
@@ -25,40 +26,83 @@
 Checksums are operating on files.
 """
 
+# This is ~16 MB
+FILE_CHUNK_SIZE = 2**24
+
 
 def _hash_mod(bitsize, hmodule):
     """
-    Return a hashing class returning hashes with a `bitsize` bit length. The
-    interface of this class is similar to the hash module API.
+    Return a hasher class that returns hashes with a ``bitsize`` bit length. The interface of this
+    class is similar to the hash module API.
     """
 
-    class hasher(object):
-        def __init__(self, msg=None):
+    class hasher(Hashable):
+        """A hasher class that behaves like a hashlib module."""
+
+        def __init__(self, msg=None, **kwargs):
+            """
+            Return a hasher, populated with an initial ``msg`` bytes string.
+            Close on the bitsize and hmodule
+            """
+            # length of binary digest for this hash
             self.digest_size = bitsize // 8
-            self.h = msg and hmodule(msg).digest()[: self.digest_size] or None
 
-        def digest(self):
-            return bytes(self.h)
+            # binh = binary hasher module
+            self.binh = hmodule()
 
-        def hexdigest(self):
-            return self.h and binascii.hexlify(self.h).decode("utf-8")
+            # msg_len = length in bytes of the message hashed
+            self.msg_len = 0
 
-        def b64digest(self):
-            return self.h and urlsafe_b64encode(self.h).decode("utf-8")
+            if msg:
+                self.update(msg)
 
-        def intdigest(self):
-            return self.h and int(bin_to_num(self.h))
+        def update(self, msg=None):
+            """
+            Update this hash with a ``msg`` bytes string.
+            """
+            if msg:
+                self.binh.update(msg)
+                self.msg_len += len(msg)
 
     return hasher
 
 
-# for FIPS support
+class Hashable:
+    """
+    A mixin for hashers that provides the base methods.
+    """
+
+    def digest(self):
+        """
+        Return a bytes string digest for this hash.
+        """
+        if not self.msg_len:
+            return
+        return self.binh.digest()[: self.digest_size]
+
+    def hexdigest(self):
+        """
+        Return a string hex digest for this hash.
+        """
+        return self.msg_len and binascii.hexlify(self.digest()).decode("utf-8")
+
+    def b64digest(self):
+        """
+        Return a string base64 digest for this hash.
+        """
+        return self.msg_len and urlsafe_b64encode(self.digest()).decode("utf-8")
+
+    def intdigest(self):
+        """
+        Return a int digest for this hash.
+        """
+        return self.msg_len and int(bin_to_num(self.digest()))
+
+
+# for FIPS support, we declare that "usedforsecurity" is False
 sys_v0 = sys.version_info[0]
 sys_v1 = sys.version_info[1]
-if sys_v0 == 3 and sys_v1 >= 9:
-    md5_hasher = partial(hashlib.md5, usedforsecurity=False)
-else:
-    md5_hasher = hashlib.md5
+md5_hasher = partial(hashlib.md5, usedforsecurity=False)
 
 
 # Base hashers for each bit size
@@ -82,31 +126,65 @@ def get_hasher(bitsize):
     return _hashmodules_by_bitsize[bitsize]
 
 
-class sha1_git_hasher(object):
+class sha1_git_hasher(Hashable):
     """
     Hash content using the git blob SHA1 convention.
+    See https://git-scm.com/book/en/v2/Git-Internals-Git-Objects#_object_storage
     """
 
-    def __init__(self, msg=None):
+    def __init__(self, msg=None, total_length=0, **kwargs):
+        """
+        Initialize a sha1_git_hasher with an optional ``msg`` byte string. The ``total_length`` of
+        all content that will be hashed, combining the ``msg`` length plus any later call to
+        update() with additional messages.
+
+        Here ``total_length`` is total length in bytes of all the messages (chunks) hashed
+        in contrast to  ``msg_len`` which is the length in bytes for the optional message.
+        """
         self.digest_size = 160 // 8
-        self.h = msg and self._compute(msg) or None
+        self.msg_len = 0
 
-    def _compute(self, msg):
-        # note: bytes interpolation is new in Python 3.5
-        git_blob_msg = b"blob %d\0%s" % (len(msg), msg)
-        return hashlib.sha1(git_blob_msg).digest()
+        if msg:
+            self.msg_len = msg_len = len(msg)
 
-    def digest(self):
-        return bytes(self.h)
+            if not total_length:
+                total_length = msg_len
+            else:
+                if total_length < msg_len:
+                    raise ValueError(
+                        f"Initial msg length: {msg_len} "
+                        f"cannot be larger than the the total_length: {self.total_length}"
+                    )
 
-    def hexdigest(self):
-        return self.h and binascii.hexlify(self.h).decode("utf-8")
+        if not total_length:
+            raise ValueError("total_length cannot be zero")
 
-    def b64digest(self):
-        return self.h and urlsafe_b64encode(self.h).decode("utf-8")
+        self.total_length = total_length
+        self.binh = get_hasher(bitsize=160)(total_length=total_length)
 
-    def intdigest(self):
-        return self.h and int(bin_to_num(self.h))
+        self._hash_header()
+        if msg:
+            self.update(msg)
+
+    def _hash_header(self):
+        # note: bytes interpolation is new in Python 3.5
+        git_blob_header = b"blob %d\0" % (self.total_length)
+        self.binh.update(msg=git_blob_header)
+
+    def update(self, msg=None):
+        """
+        Update this hash with a ``msg`` bytes string.
+        """
+        if msg:
+            msg_len = len(msg)
+            if (msg_len + self.msg_len) > self.total_length:
+                raise ValueError(
+                    f"Actual combined msg lengths: initial: {self.msg_len} plus added: {msg_len} "
+                    f"cannot be larger than the the total_length: {self.total_length}"
+                )
+
+            self.binh.update(msg)
+            self.msg_len += msg_len
 
 
 _hashmodules_by_name = {
@@ -119,25 +197,60 @@ def intdigest(self):
 }
 
 
+def get_hasher_instance_by_name(name, total_length=0):
+    """
+    Return a hasher instance for a checksum algorithm ``name`` with a planned ``total_length`` of
+    bytes to hash.
+    """
+    try:
+        hm = _hashmodules_by_name[name]
+        return hm(total_length=total_length)
+    except KeyError:
+        raise ValueError(f"Unknown checksum algorithm: {name!r}")
+
+
+def get_file_size(location):
+    return os.path.getsize(location)
+
+
 def checksum(location, name, base64=False):
     """
-    Return a checksum of `bitsize` length from the content of the file at
-    `location`. The checksum is a hexdigest or base64-encoded is `base64` is
-    True.
+    Return a checksum from the content of the file at ``location`` using the ``name`` checksum
+    algorithm. The checksum is a string as a hexdigest or is base64-encoded is ``base64`` is True.
     """
     if not filetype.is_file(location):
         return
-    hasher = _hashmodules_by_name[name]
 
-    # fixme: we should read in chunks?
-    with open(location, "rb") as f:
-        hashable = f.read()
+    total_length = get_file_size(location)
+    chunks = binary_chunks(location)
+    return checksum_from_chunks(chunks=chunks, total_length=total_length, name=name, base64=base64)
+
 
-    hashed = hasher(hashable)
+def checksum_from_chunks(chunks, name, total_length=0, base64=False):
+    """
+    Return a checksum from the content of the iterator of byte strings ``chunks`` with a
+    ``total_length`` combined length using the ``name`` checksum algorithm. The returned checksum is
+    a string as a hexdigest or is base64-encoded is ``base64`` is True.
+    """
+    hasher = get_hasher_instance_by_name(name=name, total_length=total_length)
+    for chunk in chunks:
+        hasher.update(chunk)
     if base64:
-        return hashed.b64digest()
+        return hasher.b64digest()
+    return hasher.hexdigest()
+
 
-    return hashed.hexdigest()
+def binary_chunks(location, size=FILE_CHUNK_SIZE):
+    """
+    Read file at ``location`` as binary and yield bytes of up to ``size`` length in bytes,
+    defaulting to 2**24 bytes, e.g., about 16 MB.
+    """
+    with open(location, "rb") as f:
+        while True:
+            chunk = f.read(size)
+            if not chunk:
+                break
+            yield chunk
 
 
 def md5(location):
@@ -166,19 +279,24 @@ def sha1_git(location):
 
 def multi_checksums(location, checksum_names=("md5", "sha1", "sha256", "sha512", "sha1_git")):
     """
-    Return a mapping of hexdigest checksums keyed by checksum name from the content
-    of the file at `location`. Use the `checksum_names` list of checksum names.
-    The mapping is guaranted to contains all the requested names as keys.
-    If the location is not a file, the values are None.
+    Return a mapping of hexdigest checksum strings keyed by checksum algorithm name from hashing the
+    content of the file at ``location``. Use the ``checksum_names`` list of checksum names. The
+    mapping is guaranted to contains all the requested names as keys. If the location is not a file,
+    or if the file is empty, the values are None.
+
+    The purpose of this function is to avoid read the same file multiple times
+    to compute different checksums.
     """
-    results = dict([(name, None) for name in checksum_names])
     if not filetype.is_file(location):
-        return results
-
-    # fixme: we should read in chunks?
-    with open(location, "rb") as f:
-        hashable = f.read()
-
-    for name in checksum_names:
-        results[name] = _hashmodules_by_name[name](hashable).hexdigest()
-    return results
+        return {name: None for name in checksum_names}
+    file_size = get_file_size(location)
+    hashers = {
+        name: get_hasher_instance_by_name(name=name, total_length=file_size)
+        for name in checksum_names
+    }
+
+    for chunk in binary_chunks(location):
+        for hasher in hashers.values():
+            hasher.update(msg=chunk)
+
+    return {name: hasher.hexdigest() for name, hasher in hashers.items()}
diff --git a/src/commoncode/resource.py b/src/commoncode/resource.py
index 6ce1536..5a0fa34 100644
--- a/src/commoncode/resource.py
+++ b/src/commoncode/resource.py
@@ -511,7 +511,8 @@ def _create_resources_from_paths(self, root, paths):
                     )
                     if not newpar:
                         raise Exception(
-                            f"ERROR: Codebase._create_resources_from_paths: cannot create parent for: {parent_path!r}"
+                            "ERROR: Codebase._create_resources_from_paths:"
+                            f" cannot create parent for: {parent_path!r}"
                         )
                     parent = newpar
 
@@ -1686,7 +1687,7 @@ def _get_scan_data_helper(self, location):
         """
         try:
             return json.loads(location)
-        except:
+        except Exception:
             location = abspath(normpath(expanduser(location)))
             with open(location) as f:
                 scan_data = json.load(f)
@@ -1842,7 +1843,7 @@ def _populate(self, scan_data):
         ##########################################################
         for attr_name in self.codebase_attributes:
             value = scan_data.get(attr_name)
-            if value == None:
+            if not value:
                 continue
             setattr(self.attributes, attr_name, value)
 
diff --git a/src/commoncode/system.py b/src/commoncode/system.py
index 0566a6c..ea6f7d3 100644
--- a/src/commoncode/system.py
+++ b/src/commoncode/system.py
@@ -113,12 +113,13 @@ def has_case_sensitive_fs():
     case sensitive by default, newer macOS use APFS which is no longer case
     sensitive by default.
 
-    From https://developer.apple.com/library/archive/documentation/FileManagement/Conceptual/APFS_Guide/FAQ/FAQ.html
-        How does Apple File System handle filenames?
-        APFS accepts only valid UTF-8 encoded filenames for creation, and preserves
-        both case and normalization of the filename on disk in all variants. APFS,
-        like HFS+, is case-sensitive on iOS and is available in case-sensitive and
-        case-insensitive variants on macOS, with case-insensitive being the default.
+    From
+    https://developer.apple.com/library/archive/documentation/FileManagement/Conceptual/APFS_Guide/FAQ/FAQ.html
+    How does Apple File System handle filenames?
+    APFS accepts only valid UTF-8 encoded filenames for creation, and preserves
+    both case and normalization of the filename on disk in all variants. APFS,
+    like HFS+, is case-sensitive on iOS and is available in case-sensitive and
+    case-insensitive variants on macOS, with case-insensitive being the default.
     """
     return not os.path.exists(__file__.upper())
 
diff --git a/src/commoncode/text.py b/src/commoncode/text.py
index ab56b0a..04df60f 100644
--- a/src/commoncode/text.py
+++ b/src/commoncode/text.py
@@ -38,7 +38,7 @@ def lines(s):
     splitlines.
     """
     # FIXME: leverage new Pythin 3.8 scopeing rules
-    return [l.strip() for l in s.splitlines() if l.strip()]
+    return [line.strip() for line in s.splitlines() if line.strip()]
 
 
 def foldcase(text):
diff --git a/src/commoncode/timeutils.py b/src/commoncode/timeutils.py
index bab8dad..45caf59 100644
--- a/src/commoncode/timeutils.py
+++ b/src/commoncode/timeutils.py
@@ -83,7 +83,7 @@ def tstamp2time(stamp):
     # deal with optional microsec
     try:
         microsec = dt_ms[1]
-    except:
+    except Exception:
         microsec = None
     if microsec:
         microsec = int(microsec)
diff --git a/src/commoncode/version.py b/src/commoncode/version.py
index a99ac8d..70746e8 100644
--- a/src/commoncode/version.py
+++ b/src/commoncode/version.py
@@ -228,7 +228,8 @@ def get_nupkg_nv(filename):
     """
     Return a NameVersion tuple parsed from the .nupkg NuGet archive `filename`.
 
-    For example (taken from https://stackoverflow.com/questions/51662737/regex-to-parse-package-name-and-version-number-from-nuget-package-filenames/51662926):
+    For example (taken from
+    https://stackoverflow.com/questions/51662737/regex-to-parse-package-name-and-version-number-from-nuget-package-filenames/51662926):
         >>> get_nupkg_nv('knockoutjs.3.4.2.nupkg')
         NameVersion(name='knockoutjs', version='3.4.2')
         >>> get_nupkg_nv('log4net.2.0.8.nupkg')
diff --git a/tests/test_hash.py b/tests/test_hash.py
index 27d2865..52e36bf 100644
--- a/tests/test_hash.py
+++ b/tests/test_hash.py
@@ -6,10 +6,12 @@
 # See https://aboutcode.org for more information about nexB OSS projects.
 #
 
+import hashlib
 import os
 
 from commoncode.hash import b64sha1
 from commoncode.hash import checksum
+from commoncode.hash import checksum_from_chunks
 from commoncode.hash import get_hasher
 from commoncode.hash import md5
 from commoncode.hash import multi_checksums
@@ -174,3 +176,21 @@ def test_sha1_git_checksum(self):
             test_file = self.get_test_loc(test_file)
             # test that we match the git hash-object
             assert sha1_git(test_file) == expected_sha1_git
+
+    def test_checksum_from_chunks_can_stream_gigabytes(self):
+        chunk_16mb = b"0" * 16000000
+        chunks_3dot2gb = (chunk_16mb for _ in range(200))
+        result = checksum_from_chunks(
+            chunks=chunks_3dot2gb, total_length=16000000 * 200, name="sha1_git"
+        )
+        assert result == "494caf26c43c4473f6e930b0f5c2ecf8121bcf24"
+
+    def test_checksum_from_chunks_from_stream_is_same_as_plain(self):
+        chunk = b"0" * 16000
+        chunks = (chunk for _ in range(100))
+        result1 = checksum_from_chunks(chunks=chunks, name="sha256")
+
+        result2 = hashlib.sha256()
+        for _ in range(100):
+            result2.update(chunk)
+        assert result1 == result2.hexdigest()
diff --git a/tests/test_skeleton_codestyle.py b/tests/test_skeleton_codestyle.py
deleted file mode 100644
index 95fcb9f..0000000
--- a/tests/test_skeleton_codestyle.py
+++ /dev/null
@@ -1,36 +0,0 @@
-#
-# Copyright (c) nexB Inc. and others. All rights reserved.
-# ScanCode is a trademark of nexB Inc.
-# SPDX-License-Identifier: Apache-2.0
-# See http://www.apache.org/licenses/LICENSE-2.0 for the license text.
-# See https://github.com/nexB/skeleton for support or download.
-# See https://aboutcode.org for more information about nexB OSS projects.
-#
-
-import configparser
-import subprocess
-import unittest
-
-
-class BaseTests(unittest.TestCase):
-    def test_skeleton_codestyle(self):
-        """
-        This test shouldn't run in proliferated repositories.
-        """
-        setup_cfg = configparser.ConfigParser()
-        setup_cfg.read("setup.cfg")
-        if setup_cfg["metadata"]["name"] != "skeleton":
-            return
-
-        args = "venv/bin/black --check -l 100 setup.py etc tests"
-        try:
-            subprocess.check_output(args.split())
-        except subprocess.CalledProcessError as e:
-            print("===========================================================")
-            print(e.output)
-            print("===========================================================")
-            raise Exception(
-                "Black style check failed; please format the code using:\n"
-                "  python -m black -l 100 setup.py etc tests",
-                e.output,
-            ) from e