diff options
| -rw-r--r-- | .gitignore | 1 | ||||
| -rw-r--r-- | python-cdxj-indexer.spec | 220 | ||||
| -rw-r--r-- | sources | 1 |
3 files changed, 222 insertions, 0 deletions
@@ -0,0 +1 @@ +/cdxj_indexer-1.4.5.tar.gz diff --git a/python-cdxj-indexer.spec b/python-cdxj-indexer.spec new file mode 100644 index 0000000..4b253a2 --- /dev/null +++ b/python-cdxj-indexer.spec @@ -0,0 +1,220 @@ +%global _empty_manifest_terminate_build 0 +Name: python-cdxj-indexer +Version: 1.4.5 +Release: 1 +Summary: CDXJ Indexer for WARC and ARC files +License: Apache 2.0 +URL: https://github.com/webrecorder/cdxj-indexer +Source0: https://mirrors.nju.edu.cn/pypi/web/packages/5d/2e/c245b73d2897afc0f1eb369e30b56dae1cf8ec4762086e74b200448f1fa0/cdxj_indexer-1.4.5.tar.gz +BuildArch: noarch + +Requires: python3-warcio +Requires: python3-surt +Requires: python3-idna +Requires: python3-py3amf + +%description +CDXJ Indexer +~~~~~~~~~~~~ + +A command-line tool for generating CDXJ (and CDX) indexes from WARC and ARC files. +The indexer is a new tool redesigned for fast and flexible indexing. (Based on the indexing functionality from `pywb <https://github.com/ikreymer/pywb>`_) + +Install with ``pip install cdxj-indexer`` or install locally with ``python setup.py install`` + + +The indexer supports classic CDX index format as well as the more flexible CDXJ. With CDXJ, the indexer supports custom fields and ``request`` record access for WARC files. See the examples below and the command line ``-h`` option for latest features. (This is a work in progress). + + +Usage examples +~~~~~~~~~~~~~~~~~~~~ + +Generate CDXJ index: + +.. code:: console + + > cdxj-indexer /path/to/archive-file.warc.gz + com,example)/ 20170730223850 {"url": "http://example.com/", "mime": "text/html", "status": "200", "digest": "G7HRM7BGOKSKMSXZAHMUQTTV53QOFSMK", "length": "1219", "offset": "771", "filename": "example-20170730223917.warc.gz"} + + +CDX Index (11 field): + +.. code:: console + + > cdxj-indexer -11 /path/to/archive-file.warc.gz + CDX N b a m s k r M S V g + com,example)/ 20170730223850 http://example.com/ text/html 200 G7HRM7BGOKSKMSXZAHMUQTTV53QOFSMK - - 1219 771 example-20170730223917.warc.gz + + +More advanced use cases: add additonal http headers as fields. ``http:`` prefix specifies current record headers, while ``req.http:`` specifies corresponding request record headers. The following adds the Date, Referer headers, and the request method to the index: + +.. code:: console + + > cdxj-indexer -f req.http:method,http:date,req.http:referer /path/to/archive-file.warc.gz + com,example)/ 20170801032435 {"url": "http://example.com/", "mime": "text/html", "status": "200", "digest": "A6DESOVDZ3WLYF57CS5E4RIC4ARPWRK7", "length": "1207", "offset": "834", "filename": "temp-20170801032445.warc.gz", "req.http:method": "GET", "http:date": "Tue, 01 Aug 2017 03:24:35 GMT", "referrer": "https://webrecorder.io/temp-NU34HBNO/temp/recording-session/record/http://example.com/"} + org,iana)/domains/example 20170801032437 {"url": "http://www.iana.org/domains/example", "mime": "text/html", "status": "302", "digest": "RP3Y66FDBYBZKSFYQ4VJ4RMDA5BPDJX2", "length": "675", "offset": "2652", "filename": "temp-20170801032445.warc.gz", "req.http:method": "GET", "http:date": "Tue, 01 Aug 2017 02:35:05 GMT", "referrer": "http://example.com/"} + + +The CDXJ Indexer extends the ``Indexer`` functionality in `warcio <https://github.com/webrecorder/warcio>`_ and should be flexible to extend. + + + + + + + + +%package -n python3-cdxj-indexer +Summary: CDXJ Indexer for WARC and ARC files +Provides: python-cdxj-indexer +BuildRequires: python3-devel +BuildRequires: python3-setuptools +BuildRequires: python3-pip +%description -n python3-cdxj-indexer +CDXJ Indexer +~~~~~~~~~~~~ + +A command-line tool for generating CDXJ (and CDX) indexes from WARC and ARC files. +The indexer is a new tool redesigned for fast and flexible indexing. (Based on the indexing functionality from `pywb <https://github.com/ikreymer/pywb>`_) + +Install with ``pip install cdxj-indexer`` or install locally with ``python setup.py install`` + + +The indexer supports classic CDX index format as well as the more flexible CDXJ. With CDXJ, the indexer supports custom fields and ``request`` record access for WARC files. See the examples below and the command line ``-h`` option for latest features. (This is a work in progress). + + +Usage examples +~~~~~~~~~~~~~~~~~~~~ + +Generate CDXJ index: + +.. code:: console + + > cdxj-indexer /path/to/archive-file.warc.gz + com,example)/ 20170730223850 {"url": "http://example.com/", "mime": "text/html", "status": "200", "digest": "G7HRM7BGOKSKMSXZAHMUQTTV53QOFSMK", "length": "1219", "offset": "771", "filename": "example-20170730223917.warc.gz"} + + +CDX Index (11 field): + +.. code:: console + + > cdxj-indexer -11 /path/to/archive-file.warc.gz + CDX N b a m s k r M S V g + com,example)/ 20170730223850 http://example.com/ text/html 200 G7HRM7BGOKSKMSXZAHMUQTTV53QOFSMK - - 1219 771 example-20170730223917.warc.gz + + +More advanced use cases: add additonal http headers as fields. ``http:`` prefix specifies current record headers, while ``req.http:`` specifies corresponding request record headers. The following adds the Date, Referer headers, and the request method to the index: + +.. code:: console + + > cdxj-indexer -f req.http:method,http:date,req.http:referer /path/to/archive-file.warc.gz + com,example)/ 20170801032435 {"url": "http://example.com/", "mime": "text/html", "status": "200", "digest": "A6DESOVDZ3WLYF57CS5E4RIC4ARPWRK7", "length": "1207", "offset": "834", "filename": "temp-20170801032445.warc.gz", "req.http:method": "GET", "http:date": "Tue, 01 Aug 2017 03:24:35 GMT", "referrer": "https://webrecorder.io/temp-NU34HBNO/temp/recording-session/record/http://example.com/"} + org,iana)/domains/example 20170801032437 {"url": "http://www.iana.org/domains/example", "mime": "text/html", "status": "302", "digest": "RP3Y66FDBYBZKSFYQ4VJ4RMDA5BPDJX2", "length": "675", "offset": "2652", "filename": "temp-20170801032445.warc.gz", "req.http:method": "GET", "http:date": "Tue, 01 Aug 2017 02:35:05 GMT", "referrer": "http://example.com/"} + + +The CDXJ Indexer extends the ``Indexer`` functionality in `warcio <https://github.com/webrecorder/warcio>`_ and should be flexible to extend. + + + + + + + + +%package help +Summary: Development documents and examples for cdxj-indexer +Provides: python3-cdxj-indexer-doc +%description help +CDXJ Indexer +~~~~~~~~~~~~ + +A command-line tool for generating CDXJ (and CDX) indexes from WARC and ARC files. +The indexer is a new tool redesigned for fast and flexible indexing. (Based on the indexing functionality from `pywb <https://github.com/ikreymer/pywb>`_) + +Install with ``pip install cdxj-indexer`` or install locally with ``python setup.py install`` + + +The indexer supports classic CDX index format as well as the more flexible CDXJ. With CDXJ, the indexer supports custom fields and ``request`` record access for WARC files. See the examples below and the command line ``-h`` option for latest features. (This is a work in progress). + + +Usage examples +~~~~~~~~~~~~~~~~~~~~ + +Generate CDXJ index: + +.. code:: console + + > cdxj-indexer /path/to/archive-file.warc.gz + com,example)/ 20170730223850 {"url": "http://example.com/", "mime": "text/html", "status": "200", "digest": "G7HRM7BGOKSKMSXZAHMUQTTV53QOFSMK", "length": "1219", "offset": "771", "filename": "example-20170730223917.warc.gz"} + + +CDX Index (11 field): + +.. code:: console + + > cdxj-indexer -11 /path/to/archive-file.warc.gz + CDX N b a m s k r M S V g + com,example)/ 20170730223850 http://example.com/ text/html 200 G7HRM7BGOKSKMSXZAHMUQTTV53QOFSMK - - 1219 771 example-20170730223917.warc.gz + + +More advanced use cases: add additonal http headers as fields. ``http:`` prefix specifies current record headers, while ``req.http:`` specifies corresponding request record headers. The following adds the Date, Referer headers, and the request method to the index: + +.. code:: console + + > cdxj-indexer -f req.http:method,http:date,req.http:referer /path/to/archive-file.warc.gz + com,example)/ 20170801032435 {"url": "http://example.com/", "mime": "text/html", "status": "200", "digest": "A6DESOVDZ3WLYF57CS5E4RIC4ARPWRK7", "length": "1207", "offset": "834", "filename": "temp-20170801032445.warc.gz", "req.http:method": "GET", "http:date": "Tue, 01 Aug 2017 03:24:35 GMT", "referrer": "https://webrecorder.io/temp-NU34HBNO/temp/recording-session/record/http://example.com/"} + org,iana)/domains/example 20170801032437 {"url": "http://www.iana.org/domains/example", "mime": "text/html", "status": "302", "digest": "RP3Y66FDBYBZKSFYQ4VJ4RMDA5BPDJX2", "length": "675", "offset": "2652", "filename": "temp-20170801032445.warc.gz", "req.http:method": "GET", "http:date": "Tue, 01 Aug 2017 02:35:05 GMT", "referrer": "http://example.com/"} + + +The CDXJ Indexer extends the ``Indexer`` functionality in `warcio <https://github.com/webrecorder/warcio>`_ and should be flexible to extend. + + + + + + + + +%prep +%autosetup -n cdxj-indexer-1.4.5 + +%build +%py3_build + +%install +%py3_install +install -d -m755 %{buildroot}/%{_pkgdocdir} +if [ -d doc ]; then cp -arf doc %{buildroot}/%{_pkgdocdir}; fi +if [ -d docs ]; then cp -arf docs %{buildroot}/%{_pkgdocdir}; fi +if [ -d example ]; then cp -arf example %{buildroot}/%{_pkgdocdir}; fi +if [ -d examples ]; then cp -arf examples %{buildroot}/%{_pkgdocdir}; fi +pushd %{buildroot} +if [ -d usr/lib ]; then + find usr/lib -type f -printf "/%h/%f\n" >> filelist.lst +fi +if [ -d usr/lib64 ]; then + find usr/lib64 -type f -printf "/%h/%f\n" >> filelist.lst +fi +if [ -d usr/bin ]; then + find usr/bin -type f -printf "/%h/%f\n" >> filelist.lst +fi +if [ -d usr/sbin ]; then + find usr/sbin -type f -printf "/%h/%f\n" >> filelist.lst +fi +touch doclist.lst +if [ -d usr/share/man ]; then + find usr/share/man -type f -printf "/%h/%f.gz\n" >> doclist.lst +fi +popd +mv %{buildroot}/filelist.lst . +mv %{buildroot}/doclist.lst . + +%files -n python3-cdxj-indexer -f filelist.lst +%dir %{python3_sitelib}/* + +%files help -f doclist.lst +%{_docdir}/* + +%changelog +* Fri May 05 2023 Python_Bot <Python_Bot@openeuler.org> - 1.4.5-1 +- Package Spec generated @@ -0,0 +1 @@ +2d6cd1ef19587c70d1935f2472bba6f7 cdxj_indexer-1.4.5.tar.gz |