diff --git a/docs/uri-scheme-browse-origin.rst b/docs/uri-scheme-browse-origin.rst index efd88ad7..d17ca4c6 100644 --- a/docs/uri-scheme-browse-origin.rst +++ b/docs/uri-scheme-browse-origin.rst @@ -1,489 +1,489 @@ Origin ^^^^^^ This describes the URI scheme when one wants to browse the Software Heritage archive in the context of an origin (for instance, a repository crawled from GitHub or a Debian source package). All the views pointed by that scheme offer quick links to browse objects as found during the associated crawls performed by Software Heritage: * the root directory of the origin * the list of branches of the origin * the list of releases of the origin Origin visits """"""""""""" -.. http:get:: /browse/origin/(origin_type)/url/(origin_url)/visits/ +.. http:get:: /browse/origin/[(origin_type)/url/](origin_url)/visits/ HTML view that displays a visits reporting for a SWH origin identified by its type and url. :param string origin_type: the type of the SWH origin (*git*, *svn*, *deb* ...) :param string origin_url: the url of the origin (e.g. https://github.com/(user)/(repo)/) :statuscode 200: no error :statuscode 404: requested origin can not be found in the SWH archive **Examples:** .. parsed-literal:: :swh_web_browse:`origin/git/url/https://github.com/torvalds/linux/visits/` :swh_web_browse:`origin/git/url/https://github.com/python/cpython/visits/` - :swh_web_browse:`origin/deb/url/deb://Debian-Security/packages/mediawiki/visits/` - :swh_web_browse:`origin/git/url/https://gitorious.org/qt/qtbase.git/visits/` + :swh_web_browse:`origin/deb://Debian-Security/packages/mediawiki/visits/` + :swh_web_browse:`origin/https://gitorious.org/qt/qtbase.git/visits/` Origin directory """""""""""""""" -.. http:get:: /browse/origin/(origin_type)/url/(origin_url)/directory/[(path)/] +.. http:get:: /browse/origin/[(origin_type)/url/](origin_url)/directory/[(path)/] HTML view for browsing the content of a directory reachable from the root directory (including itself) associated to the latest full visit of a SWH origin. The content of the directory is first sorted in lexicographical order and the sub-directories are displayed before the regular files. The view enables to navigate from the requested directory to directories reachable from it in a recursive way but also up to the origin root directory. A breadcrumb located in the top part of the view allows to keep track of the paths navigated so far. The view also enables to easily switch between the origin branches and releases through a dropdown menu. The origin branch (default to master) from which to retrieve the directory content can also be specified by using the branch query parameter. :param string origin_type: the type of the SWH origin (*git*, *svn*, *deb* ...) :param string origin_url: the url of the origin (e.g. https://github.com/(user)/(repo)/) :param string path: optional parameter used to specify the path of a directory reachable from the origin root one :query string branch: specify the origin branch name from which to retrieve the root directory :query string release: specify the origin release name from which to retrieve the root directory :query string revision: specify the origin revision, identified by the hexadecimal representation of its *sha1_git* value, from which to retrieve the root directory :query int visit_id: specify a SWH visit id to retrieve the directory from instead of using the latest full visit by default :statuscode 200: no error :statuscode 404: requested origin can not be found in the SWH archive or the provided path does not exist from the origin root directory **Examples:** .. parsed-literal:: :swh_web_browse:`origin/git/url/https://github.com/torvalds/linux/directory/` :swh_web_browse:`origin/git/url/https://github.com/torvalds/linux/directory/net/ethernet/` - :swh_web_browse:`origin/git/url/https://github.com/python/cpython/directory/` - :swh_web_browse:`origin/git/url/https://github.com/python/cpython/directory/Python/` - :swh_web_browse:`origin/git/url/https://github.com/python/cpython/directory/?branch=refs/heads/2.7` + :swh_web_browse:`origin/https://github.com/python/cpython/directory/` + :swh_web_browse:`origin/https://github.com/python/cpython/directory/Python/` + :swh_web_browse:`origin/https://github.com/python/cpython/directory/?branch=refs/heads/2.7` -.. http:get:: /browse/origin/(origin_type)/url/(origin_url)/visit/(timestamp)/directory/[(path)/] +.. http:get:: /browse/origin/[(origin_type)/url/](origin_url)/visit/(timestamp)/directory/[(path)/] HTML view for browsing the content of a directory reachable from the root directory (including itself) associated to a visit of a SWH origin closest to a provided timestamp. The content of the directory is first sorted in lexicographical order and the sub-directories are displayed before the regular files. The view enables to navigate from the requested directory to directories reachable from it in a recursive way but also up to the origin root directory. A breadcrumb located in the top part of the view allows to keep track of the paths navigated so far. The view also enables to easily switch between the origin branches and releases through a dropdown menu. The origin branch (default to master) from which to retrieve the directory content can also be specified by using the branch query parameter. :param string origin_type: the type of the SWH origin (*git*, *svn*, *deb* ...) :param string origin_url: the url of the origin (e.g. https://github.com/(user)/(repo)/) :param string timestamp: a date string (any format parsable by `dateutil.parser.parse`_) or Unix timestamp to parse in order to find the closest SWH visit. :param path: optional parameter used to specify the path of a directory reachable from the origin root one :type path: string :query string branch: specify the origin branch name from which to retrieve the root directory :query string release: specify the origin release name from which to retrieve the root directory :query string revision: specify the origin revision, identified by the hexadecimal representation of its *sha1_git* value, from which to retrieve the directory :query int visit_id: specify a SWH visit id to retrieve the directory from instead of using the provided timestamp :statuscode 200: no error :statuscode 404: requested origin can not be found in the SWH archive, requested visit timestamp does not exist or the provided path does not exist from the origin root directory **Examples:** .. parsed-literal:: :swh_web_browse:`origin/git/url/https://github.com/torvalds/linux/visit/1493926809/directory/` :swh_web_browse:`origin/git/url/https://github.com/torvalds/linux/visit/2016-09-14T10:36:21/directory/net/ethernet/` :swh_web_browse:`origin/git/url/https://github.com/python/cpython/visit/1474620651/directory/` :swh_web_browse:`origin/git/url/https://github.com/python/cpython/visit/2017-05-05/directory/Python/` :swh_web_browse:`origin/git/url/https://github.com/python/cpython/visit/2015-08/directory/?branch=refs/heads/2.7` Origin content """""""""""""" -.. http:get:: /browse/origin/(origin_type)/url/(origin_url)/content/(path)/ +.. http:get:: /browse/origin/[(origin_type)/url/](origin_url)/content/(path)/ HTML view that produces a display of a SWH content associated to the latest full visit of a SWH origin. If the content to display is textual, it will be highlighted client-side if possible using highlightjs_. The procedure to perform that task is described in :http:get:`/browse/content/[(algo_hash):](hash)/`. It is also possible to highlight specific lines of a textual content (not in terms of syntax highlighting but to emphasize some relevant content part) by either: * clicking on line numbers (holding shift to highlight a lines range) * using an url fragment in the form '#Ln' or '#Lm-Ln' The view displays a breadcrumb on top of the rendered content in order to easily navigate up to the origin root directory. The view also enables to easily switch between the origin branches and releases through a dropdown menu. The origin branch (default to master) from which to retrieve the content can also be specified by using the branch query parameter. :param string origin_type: the type of the SWH origin (*git*, *svn*, *deb* ...) :param string origin_url: the url of the origin (e.g. https://github.com/(user)/(repo)/) :param string path: path of a content reachable from the origin root directory :query string branch: specify the origin branch name from which to retrieve the content :query string release: specify the origin release name from which to retrieve the content :query string revision: specify the origin revision, identified by the hexadecimal representation of its *sha1_git* value, from which to retrieve the content :query int visit_id: specify a SWH visit id to retrieve the content from instead of using the latest full visit by default :statuscode 200: no error :statuscode 404: requested origin can not be found in the SWH archive, or the provided content path does not exist from the origin root directory **Examples:** .. parsed-literal:: :swh_web_browse:`origin/git/url/https://github.com/git/git/content/git.c/` :swh_web_browse:`origin/git/url/https://github.com/git/git/content/git.c/` - :swh_web_browse:`origin/git/url/https://github.com/mozilla/gecko-dev/content/js/src/json.cpp/` - :swh_web_browse:`origin/git/url/https://github.com/git/git/content/git.c/?branch=refs/heads/next` + :swh_web_browse:`origin/https://github.com/mozilla/gecko-dev/content/js/src/json.cpp/` + :swh_web_browse:`origin/https://github.com/git/git/content/git.c/?branch=refs/heads/next` -.. http:get:: /browse/origin/(origin_type)/url/(origin_url)/visit/(timestamp)/content/(path)/ +.. http:get:: /browse/origin/[(origin_type)/url/](origin_url)/visit/(timestamp)/content/(path)/ HTML view that produces a display of a SWH content associated to a visit of a SWH origin closest to a provided timestamp. If the content to display is textual, it will be highlighted client-side if possible using highlightjs_. The procedure to perform that task is described in :http:get:`/browse/content/[(algo_hash):](hash)/`. It is also possible to highlight specific lines of a textual content (not in terms of syntax highlighting but to emphasize some relevant content part) by either: * clicking on line numbers (holding shift to highlight a lines range) * using an url fragment in the form '#Ln' or '#Lm-Ln' The view displays a breadcrumb on top of the rendered content in order to easily navigate up to the origin root directory. The view also enables to easily switch between the origin branches and releases through a dropdown menu. The origin branch (default to master) from which to retrieve the content can also be specified by using the branch query parameter. :param string origin_type: the type of the SWH origin (*git*, *svn*, *deb* ...) :param string origin_url: the url of the origin (e.g. https://github.com/(user)/(repo)/) :param string timestamp: a date string (any format parsable by `dateutil.parser.parse`_) or Unix timestamp to parse in order to find the closest SWH visit. :param string path: path of a content reachable from the origin root directory :query string branch: specify the origin branch name from which to retrieve the content :query string release: specify the origin release name from which to retrieve the content :query string revision: specify the origin revision, identified by the hexadecimal representation of its *sha1_git* value, from which to retrieve the content :query int visit_id: specify a SWH visit id to retrieve the content from instead of using the provided timestamp :statuscode 200: no error :statuscode 404: requested origin can not be found in the SWH archive, requested visit timestamp does not exist or the provided content path does not exist from the origin root directory **Examples:** .. parsed-literal:: :swh_web_browse:`origin/git/url/https://github.com/git/git/visit/1473933564/content/git.c/` :swh_web_browse:`origin/git/url/https://github.com/git/git/visit/2016-05-05T00:0:00+00:00/content/git.c/` - :swh_web_browse:`origin/git/url/https://github.com/mozilla/gecko-dev/visit/1490126182/content/js/src/json.cpp/` - :swh_web_browse:`origin/git/url/https://github.com/mozilla/gecko-dev/visit/2017-03-21/content/js/src/json.cpp/#L904-L931` - :swh_web_browse:`origin/git/url/https://github.com/git/git/visit/2017-09-15/content/git.c/?branch=refs/heads/next` + :swh_web_browse:`origin/https://github.com/mozilla/gecko-dev/visit/1490126182/content/js/src/json.cpp/` + :swh_web_browse:`origin/https://github.com/mozilla/gecko-dev/visit/2017-03-21/content/js/src/json.cpp/#L904-L931` + :swh_web_browse:`origin/https://github.com/git/git/visit/2017-09-15/content/git.c/?branch=refs/heads/next` Origin history """""""""""""" -.. http:get:: /browse/origin/(origin_type)/url/(origin_url)/log/ +.. http:get:: /browse/origin/[(origin_type)/url/](origin_url)/log/ HTML view that produces a display of revisions history heading to the last revision found during the latest visit of a SWH origin. In other words, it shows the commit log associated to the latest full visit of a SWH origin. The following data are displayed for each log entry: * author of the revision * link to the revision metadata * message associated the revision * date of the revision * link to browse the associated source tree in the origin context N log entries are displayed per page (default is 20). In order to navigate in a large history, two buttons are present at the bottom of the view: * *Newer*: fetch and display if available the N more recent log entries than the ones currently displayed * *Older*: fetch and display if available the N older log entries than the ones currently displayed The view also enables to easily switch between the origin branches and releases through a dropdown menu. The origin branch (default to master) from which to retrieve the content can also be specified by using the branch query parameter. :param string origin_type: the type of the SWH origin (*git*, *svn*, *deb* ...) :param string origin_url: the url of the origin (e.g. https://github.com/(user)/(repo)/) :query string revs_breadcrumb: used internally to store the navigation breadcrumbs (i.e. the list of descendant revisions visited so far). It must be a string in the form "(rev_1)[/(rev_2)/.../(rev_n)]" where rev_i corresponds to a revision *sha1_git*. :query int per_page: the number of log entries to display per page (default is 20, max is 50) :query string branch: specify the origin branch name from which to retrieve the commit log :query string release: specify the origin release name from which to retrieve the commit log :query string revision: specify the origin revision, identified by the hexadecimal representation of its *sha1_git* value, from which to retrieve the commit log :query int visit_id: specify a SWH visit id to retrieve the history log from instead of using the latest visit by default :statuscode 200: no error :statuscode 404: requested origin can not be found in the SWH archive **Examples:** .. parsed-literal:: :swh_web_browse:`origin/git/url/https://github.com/videolan/vlc/log/` - :swh_web_browse:`origin/git/url/https://github.com/Kitware/CMake/log/` - :swh_web_browse:`origin/git/url/https://github.com/Kitware/CMake/log/?branch=refs/heads/release` + :swh_web_browse:`origin/https://github.com/Kitware/CMake/log/` + :swh_web_browse:`origin/https://github.com/Kitware/CMake/log/?branch=refs/heads/release` -.. http:get:: /browse/origin/(origin_type)/url/(origin_url)/visit/(timestamp)/log/ +.. http:get:: /browse/origin/[(origin_type)/url/](origin_url)/visit/(timestamp)/log/ HTML view that produces a display of revisions history heading to the last revision found during a visit of a SWH origin closest to the provided timestamp. In other words, it shows the commit log associated to a visit of a SWH origin closest to a provided timestamp. The following data are displayed for each log entry: * author of the revision * link to the revision metadata * message associated the revision * date of the revision * link to browse the associated source tree in the origin context N log entries are displayed per page (default is 20). In order to navigate in a large history, two buttons are present at the bottom of the view: * *Newer*: fetch and display if available the N more recent log entries than the ones currently displayed * *Older*: fetch and display if available the N older log entries than the ones currently displayed The view also enables to easily switch between the origin branches and releases through a dropdown menu. The origin branch (default to master) from which to retrieve the content can also be specified by using the branch query parameter. :param string origin_type: the type of the SWH origin (*git*, *svn*, *deb* ...) :param string origin_url: the url of the origin (e.g. https://github.com/(user)/(repo)/) :param string timestamp: a date string (any format parsable by `dateutil.parser.parse`_) or Unix timestamp to parse in order to find the closest SWH visit. :query string revs_breadcrumb: used internally to store the navigation breadcrumbs (i.e. the list of descendant revisions visited so far). It must be a string in the form "(rev_1)[/(rev_2)/.../(rev_n)]" where rev_i corresponds to a revision *sha1_git*. :query int per_page: the number of log entries to display per page (default is 20, max is 50) :query string branch: specify the origin branch name from which to retrieve the commit log :query string release: specify the origin release name from which to retrieve the commit log :query string revision: specify the origin revision, identified by the hexadecimal representation of its *sha1_git* value, from which to retrieve the commit log :query int visit_id: specify a SWH visit id to retrieve the history log from instead of using the provided timestamp :statuscode 200: no error :statuscode 404: requested origin can not be found in the SWH archive **Examples:** .. parsed-literal:: :swh_web_browse:`origin/git/url/https://github.com/videolan/vlc/visit/1459651262/log/` :swh_web_browse:`origin/git/url/https://github.com/Kitware/CMake/visit/2016-04-01/log/` - :swh_web_browse:`origin/git/url/https://github.com/Kitware/CMake/visit/1438116814/log/?branch=refs/heads/release` - :swh_web_browse:`origin/git/url/https://github.com/Kitware/CMake/visit/2017-05-05T03:14:23/log/?branch=refs/heads/release` + :swh_web_browse:`origin/https://github.com/Kitware/CMake/visit/1438116814/log/?branch=refs/heads/release` + :swh_web_browse:`origin/https://github.com/Kitware/CMake/visit/2017-05-05T03:14:23/log/?branch=refs/heads/release` Origin branches """"""""""""""" -.. http:get:: /browse/origin/(origin_type)/url/(origin_url)/branches/ +.. http:get:: /browse/origin/[(origin_type)/url/](origin_url)/branches/ HTML view that produces a display of the list of branches found during the latest full visit of a SWH origin. The following data are displayed for each branch: * its name * a link to browse the associated directory * a link to browse the associated revision * last commit message * last commit date That list of branches is paginated, each page displaying a maximum of 20 branches. :param string origin_type: the type of the SWH origin (*git*, *svn*, *deb* ...) :param string origin_url: the url of the origin (e.g. https://github.com/(user)/(repo)/) :statuscode 200: no error :statuscode 404: requested origin can not be found in the SWH archive **Examples:** .. parsed-literal:: :swh_web_browse:`origin/deb/url/deb://Debian/packages/linux/branches/` - :swh_web_browse:`origin/git/url/https://github.com/webpack/webpack/branches/` + :swh_web_browse:`origin/https://github.com/webpack/webpack/branches/` -.. http:get:: /browse/origin/(origin_type)/url/(origin_url)/visit/(timestamp)/branches/ +.. http:get:: /browse/origin/[(origin_type)/url/](origin_url)/visit/(timestamp)/branches/ HTML view that produces a display of the list of branches found during a visit of a SWH origin closest to the provided timestamp. The following data are displayed for each branch: * its name * a link to browse the associated directory * a link to browse the associated revision * last commit message * last commit date That list of branches is paginated, each page displaying a maximum of 20 branches. :param string origin_type: the type of the SWH origin (*git*, *svn*, *deb* ...) :param string origin_url: the url of the origin (e.g. https://github.com/(user)/(repo)/) :param string timestamp: a date string (any format parsable by `dateutil.parser.parse`_) or Unix timestamp to parse in order to find the closest SWH visit. :statuscode 200: no error :statuscode 404: requested origin can not be found in the SWH archive **Examples:** .. parsed-literal:: :swh_web_browse:`origin/git/url/https://github.com/kripken/emscripten/visit/2017-05-05T12:02:03/branches/` - :swh_web_browse:`origin/deb/url/deb://Debian/packages/apache2-mod-xforward/visit/2017-11-15T05:15:09/branches/` + :swh_web_browse:`origin/deb://Debian/packages/apache2-mod-xforward/visit/2017-11-15T05:15:09/branches/` Origin releases """"""""""""""" -.. http:get:: /browse/origin/(origin_type)/url/(origin_url)/releases/ +.. http:get:: /browse/origin/[(origin_type)/url/](origin_url)/releases/ HTML view that produces a display of the list of releases found during the latest full visit of a SWH origin. The following data are displayed for each release: * its name * a link to browse the release details * its target type (revision, directory, content or release) * its associated message * its date That list of releases is paginated, each page displaying a maximum of 20 releases. :param string origin_type: the type of the SWH origin (*git*, *svn*, *deb* ...) :param string origin_url: the url of the origin (e.g. https://github.com/(user)/(repo)/) :statuscode 200: no error :statuscode 404: requested origin can not be found in the SWH archive **Examples:** .. parsed-literal:: :swh_web_browse:`origin/git/url/https://github.com/git/git/releases/` - :swh_web_browse:`origin/git/url/https://github.com/webpack/webpack/releases/` + :swh_web_browse:`origin/https://github.com/webpack/webpack/releases/` -.. http:get:: /browse/origin/(origin_type)/url/(origin_url)/visit/(timestamp)/releases/ +.. http:get:: /browse/origin/[(origin_type)/url/](origin_url)/visit/(timestamp)/releases/ HTML view that produces a display of the list of releases found during a visit of a SWH origin closest to the provided timestamp. The following data are displayed for each release: * its name * a link to browse the release details * its target type (revision, directory, content or release) * its associated message * its date That list of releases is paginated, each page displaying a maximum of 20 releases. :param string origin_type: the type of the SWH origin (*git*, *svn*, *deb* ...) :param string origin_url: the url of the origin (e.g. https://github.com/(user)/(repo)/) :param string timestamp: a date string (any format parsable by `dateutil.parser.parse`_) or Unix timestamp to parse in order to find the closest SWH visit. :statuscode 200: no error :statuscode 404: requested origin can not be found in the SWH archive **Examples:** .. parsed-literal:: :swh_web_browse:`origin/git/url/https://github.com/torvalds/linux/visit/2017-11-21T19:37:42/releases/` - :swh_web_browse:`origin/git/url/https://github.com/Kitware/CMake/visit/2016-09-23T14:06:35/releases/` + :swh_web_browse:`origin/https://github.com/Kitware/CMake/visit/2016-09-23T14:06:35/releases/` .. _highlightjs: https://highlightjs.org/ .. _dateutil.parser.parse: http://dateutil.readthedocs.io/en/stable/parser.html diff --git a/docs/uri-scheme-browse-snapshot.rst b/docs/uri-scheme-browse-snapshot.rst index 50bc9a16..1be08033 100644 --- a/docs/uri-scheme-browse-snapshot.rst +++ b/docs/uri-scheme-browse-snapshot.rst @@ -1,187 +1,187 @@ Snapshot ^^^^^^^^ .. http:get:: /browse/snapshot/(snapshot_id)/ HTML view that displays the content of a SWH snapshot from its identifier (see :func:`swh.model.identifiers.snapshot_identifier` in our data model module for details about how they are computed). A snapshot is a set of named branches, which are pointers to objects at any level of the Software Heritage DAG. It represents a full picture of an origin at a given time. Thus, multiple visits of different origins can point to the same snapshot (for instance, when several projects are forks of a common one). Currently, that endpoint simply performs a redirection to :http:get:`/browse/snapshot/(snapshot_id)/directory/[(path)/]` in order to display the root directory associated to the default snapshot branch (usually master). :param string snapshot_id: hexadecimal representation of the snapshot *sha1* identifier :statuscode 200: no error :statuscode 400: an invalid snapshot identifier has been provided :statuscode 404: requested snapshot can not be found in the SWH archive **Examples:** .. parsed-literal:: :swh_web_browse:`snapshot/baebc2109e4a2ec22a1129a3859647e191d04df4/` :swh_web_browse:`snapshot/673156c31a876c5b99b2fe3e89615529de9a3c44/` Snapshot directory """""""""""""""""" .. http:get:: /browse/snapshot/(snapshot_id)/directory/[(path)/] HTML view that displays the content of a directory reachable from a SWH snapshot. The features offered by the view are similar to the one for browsing a directory in an origin context - (see :http:get:`/browse/origin/(origin_type)/url/(origin_url)/directory/[(path)/]`). + (see :http:get:`/browse/origin/[(origin_type)/url/](origin_url)/directory/[(path)/]`). :param string snapshot_id: hexadecimal representation of the snapshot *sha1* identifier :param string path: optional parameter used to specify the path of a directory reachable from the snapshot root one :query string branch: specify the snapshot branch name from which to retrieve the root directory :query string release: specify the snapshot release name from which to retrieve the root directory :query string revision: specify the snapshot revision, identified by the hexadecimal representation of its *sha1_git* value, from which to retrieve the root directory :statuscode 200: no error :statuscode 400: an invalid snapshot identifier has been provided :statuscode 404: requested snapshot can not be found in the SWH archive **Examples:** .. parsed-literal:: :swh_web_browse:`snapshot/baebc2109e4a2ec22a1129a3859647e191d04df4/directory/drivers/gpu/` :swh_web_browse:`snapshot/673156c31a876c5b99b2fe3e89615529de9a3c44/directory/src/opengl/` :swh_web_browse:`snapshot/673156c31a876c5b99b2fe3e89615529de9a3c44/log/?release=v5.7.0` Snapshot content """""""""""""""" .. http:get:: /browse/snapshot/(snapshot_id)/content/(path)/ HTML view that produces a display of a SWH content reachable from a SWH snapshot. The features offered by the view are similar to the one for browsing a content in an origin context - (see :http:get:`/browse/origin/(origin_type)/url/(origin_url)/content/(path)/`). + (see :http:get:`/browse/origin/[(origin_type)/url/](origin_url)/content/(path)/`). :param string snapshot_id: hexadecimal representation of the snapshot *sha1* identifier :param string path: path of a content reachable from the snapshot root directory :query string branch: specify the snapshot branch name from which to retrieve the content :query string release: specify the snapshot release name from which to retrieve the content :query string revision: specify the snapshot revision, identified by the hexadecimal representation of its *sha1_git* value, from which to retrieve the content :statuscode 200: no error :statuscode 400: an invalid snapshot identifier has been provided :statuscode 404: requested snapshot can not be found in the SWH archive, or the provided content path does not exist from the origin root directory **Examples:** .. parsed-literal:: :swh_web_browse:`snapshot/baebc2109e4a2ec22a1129a3859647e191d04df4/content/init/initramfs.c` :swh_web_browse:`snapshot/673156c31a876c5b99b2fe3e89615529de9a3c44/content/src/opengl/qglbuffer.h/` :swh_web_browse:`snapshot/673156c31a876c5b99b2fe3e89615529de9a3c44/content/src/opengl/qglbuffer.h/?release=v5.0.0` Snapshot history """""""""""""""" .. http:get:: /browse/snapshot/(snapshot_id)/log/ HTML view that produces a display of revisions history (aka the commit log) heading to the last revision collected in a SWH snasphot. The features offered by the view are similar to the one for browsing the history in an origin context - (see :http:get:`/browse/origin/(origin_type)/url/(origin_url)/log/`). + (see :http:get:`/browse/origin/[(origin_type)/url/](origin_url)/log/`). :param string snapshot_id: hexadecimal representation of the snapshot *sha1* identifier :query string revs_breadcrumb: used internally to store the navigation breadcrumbs (i.e. the list of descendant revisions visited so far). It must be a string in the form "(rev_1)[/(rev_2)/.../(rev_n)]" where rev_i corresponds to a revision *sha1_git*. :query int per_page: the number of log entries to display per page (default is 20, max is 50) :query string branch: specify the snapshot branch name from which to retrieve the commit log :query string release: specify the snasphot release name from which to retrieve the commit log :query string revision: specify the snapshot revision, identified by the hexadecimal representation of its *sha1_git* value, from which to retrieve the commit log :statuscode 200: no error :statuscode 400: an invalid snapshot identifier has been provided :statuscode 404: requested snapshot can not be found in the SWH archive **Examples:** .. parsed-literal:: :swh_web_browse:`snapshot/a274b44111f777209556e94920b7e71cf5c305cd/log/` :swh_web_browse:`snapshot/9ca9e75279df5f4e3fee19bf5190ed672dcdfb33/log/?branch=refs/heads/emacs-unicode` Snapshot branches """"""""""""""""" .. http:get:: /browse/snapshot/(snapshot_id)/branches/ HTML view that produces a display of the list of branches collected in a SWH snapshot. The features offered by the view are similar to the one for browsing the list of branches in an origin context - (see :http:get:`/browse/origin/(origin_type)/url/(origin_url)/branches/`). + (see :http:get:`/browse/origin/[(origin_type)/url/](origin_url)/branches/`). :param string snapshot_id: hexadecimal representation of the snapshot *sha1* identifier :statuscode 200: no error :statuscode 400: an invalid snapshot identifier has been provided :statuscode 404: requested snapshot can not be found in the SWH archive **Examples:** .. parsed-literal:: :swh_web_browse:`snapshot/03d7897352541e78ee7b13a580dc836778e8126a/branches/` :swh_web_browse:`snapshot/f37563b953327f8fd83e39af6ebb929ef85103d5/branches/` Snapshot releases """"""""""""""""" .. http:get:: /browse/snapshot/(snapshot_id)/releases/ HTML view that produces a display of the list of releases collected in a SWH snapshot. The features offered by the view are similar to the one for browsing the list of releases in an origin context - (see :http:get:`/browse/origin/(origin_type)/url/(origin_url)/releases/`). + (see :http:get:`/browse/origin/[(origin_type)/url/](origin_url)/releases/`). :param string snapshot_id: hexadecimal representation of the snapshot *sha1* identifier :statuscode 200: no error :statuscode 400: an invalid snapshot identifier has been provided :statuscode 404: requested snapshot can not be found in the SWH archive **Examples:** .. parsed-literal:: :swh_web_browse:`snapshot/673156c31a876c5b99b2fe3e89615529de9a3c44/releases/` :swh_web_browse:`snapshot/23e6fb084a60cc909b9e222d80d89fdb98756dee/releases/` \ No newline at end of file diff --git a/docs/uri-scheme-browse.rst b/docs/uri-scheme-browse.rst index 3b9263bb..1021f5ae 100644 --- a/docs/uri-scheme-browse.rst +++ b/docs/uri-scheme-browse.rst @@ -1,101 +1,101 @@ URI scheme for SWH Web Browse application ========================================= This web application aims to provide HTML views to easily navigate in the SWH archive, thus it needs to be reached from a web browser. If you intend to query the SWH archive programmatically through any HTTP client, please refer to the :ref:`swh-web-api-urls` section instead. Context-independent browsing ---------------------------- Context-independent URLs provide information about SWH objects (e.g., revisions, directories, contents, person, ...), independently of the contexts where they have been found (e.g., specific repositories, branches, commits, ...). The following endpoints are the same of the API case (see below), and just render the corresponding information for user consumption. Where hyperlinks are created, they always point to other context-independent user URLs: * :http:get:`/browse/content/[(algo_hash):](hash)/`: Display a SWH content * :http:get:`/browse/content/[(algo_hash):](hash)/raw/`: Get / Download SWH content raw data * :http:get:`/browse/directory/(sha1_git)/[(path)/]`: Browse the content of a SWH directory * :http:get:`/browse/person/(person_id)/`: Information on a SWH person * :http:get:`/browse/revision/(sha1_git)/`: Browse a SWH revision * :http:get:`/browse/revision/(sha1_git)/log/`: Browse history log heading to a SWH revision Context-dependent browsing -------------------------- Context-dependent URLs provide information about SWH objects, limited to specific contexts where the objects have been found. For instance, instead of having to specify a (root) revision by *sha1_git*, users might want to specify a place and a time. In SWH a "place" is an origin, with an optional branch name; a "time" is a timestamp at which some place has been observed by SWH crawlers. Wherever a revision context is expected in a path (i.e., a **/browse/revision/(sha1_git)/** path fragment) we can put in its stead a path fragment of the form **/origin/(origin_type)/url/(origin_url)/[/visit/(timestamp)/][?branch=(branch)]**. Such a fragment is resolved, internally by the SWH archive, to a revision *sha1_git* as follows: - if *timestamp* is absent: look for the most recent crawl of origin identified by *origin_type* and *origin_url* - if *timestamp* is given: look for the closest crawl of origin identified by *origin_type* and *origin_url* from timestamp *timestamp* - if *branch* is given as a query parameter: look for the branch *branch* - if *branch* is absent: look for branch "HEAD" or "master" - return the revision *sha1_git* pointed by the chosen branch The already mentioned URLs for revision contexts can therefore be alternatively specified by users as: -* :http:get:`/browse/origin/(origin_type)/url/(origin_url)/directory/[(path)/]` -* :http:get:`/browse/origin/(origin_type)/url/(origin_url)/visit/(timestamp)/directory/[(path)/]` -* :http:get:`/browse/origin/(origin_type)/url/(origin_url)/content/(path)/` -* :http:get:`/browse/origin/(origin_type)/url/(origin_url)/visit/(timestamp)/content/(path)/` -* :http:get:`/browse/origin/(origin_type)/url/(origin_url)/log/` -* :http:get:`/browse/origin/(origin_type)/url/(origin_url)/visit/(timestamp)/log/` +* :http:get:`/browse/origin/[(origin_type)/url/](origin_url)/directory/[(path)/]` +* :http:get:`/browse/origin/[(origin_type)/url/](origin_url)/visit/(timestamp)/directory/[(path)/]` +* :http:get:`/browse/origin/[(origin_type)/url/](origin_url)/content/(path)/` +* :http:get:`/browse/origin/[(origin_type)/url/](origin_url)/visit/(timestamp)/content/(path)/` +* :http:get:`/browse/origin/[(origin_type)/url/](origin_url)/log/` +* :http:get:`/browse/origin/[(origin_type)/url/](origin_url)/visit/(timestamp)/log/` Typing: - *origin_type* corresponds to the type of the archived origin: *git*, *svn*, *hg*, *deposit*, *deb*, ... - *origin_url* corresponds to the URL the origin was crawled from, for instance https://github.com/(user)/(repo)/ - *branch* name is given as per the corresponding VCS (e.g., Git) as a query parameter to the requestes URL. - *timestamp* is given in a format as liberal as possible, to uphold the principle of least surprise. At the very minimum it is possible to enter timestamps as: - Unix epoch timestamp (see for instance the output of `date +%s`) - ISO 8601 timestamps (see for instance the output of `date -I`, `date -Is`) - YYYY[MM[DD[HH[MM[SS]]]]] ad-hoc format - YYYY[-MM[-DD[ HH:[MM:[SS:]]]]] ad-hoc format SWH Browse Urls --------------- .. include:: uri-scheme-browse-content.rst .. include:: uri-scheme-browse-directory.rst .. include:: uri-scheme-browse-identifiers.rst .. include:: uri-scheme-browse-origin.rst .. include:: uri-scheme-browse-person.rst .. include:: uri-scheme-browse-release.rst .. include:: uri-scheme-browse-revision.rst .. include:: uri-scheme-browse-snapshot.rst diff --git a/swh/web/browse/utils.py b/swh/web/browse/utils.py index e91e6d37..beb6ec16 100644 --- a/swh/web/browse/utils.py +++ b/swh/web/browse/utils.py @@ -1,919 +1,953 @@ # Copyright (C) 2017-2018 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU Affero General Public License version 3, or any later version # See top-level LICENSE file for more information import base64 import magic import math import stat from django.core.cache import cache from django.utils.safestring import mark_safe from importlib import reload from swh.web.common import highlightjs, service from swh.web.common.exc import NotFoundExc from swh.web.common.utils import ( reverse, format_utc_iso_date, parse_timestamp ) from swh.web.config import get_config def get_directory_entries(sha1_git): """Function that retrieves the content of a SWH directory from the SWH archive. The directories entries are first sorted in lexicographical order. Sub-directories and regular files are then extracted. Args: sha1_git: sha1_git identifier of the directory Returns: A tuple whose first member corresponds to the sub-directories list and second member the regular files list Raises: NotFoundExc if the directory is not found """ cache_entry_id = 'directory_entries_%s' % sha1_git cache_entry = cache.get(cache_entry_id) if cache_entry: return cache_entry entries = list(service.lookup_directory(sha1_git)) entries = sorted(entries, key=lambda e: e['name']) for entry in entries: entry['perms'] = stat.filemode(entry['perms']) dirs = [e for e in entries if e['type'] == 'dir'] files = [e for e in entries if e['type'] == 'file'] cache.set(cache_entry_id, (dirs, files)) return dirs, files def get_mimetype_and_encoding_for_content(content): """Function that returns the mime type and the encoding associated to a content buffer using the magic module under the hood. Args: content (bytes): a content buffer Returns: A tuple (mimetype, encoding), for instance ('text/plain', 'us-ascii'), associated to the provided content. """ while True: try: magic_result = magic.detect_from_content(content) mime_type = magic_result.mime_type encoding = magic_result.encoding break except Exception as exc: # workaround an issue with the magic module who can fail # if detect_from_content is called multiple times in # a short amount of time reload(magic) return mime_type, encoding # maximum authorized content size in bytes for HTML display # with code highlighting content_display_max_size = get_config()['content_display_max_size'] def request_content(query_string, max_size=content_display_max_size): """Function that retrieves a SWH content from the SWH archive. Raw bytes content is first retrieved, then the content mime type. If the mime type is not stored in the archive, it will be computed using Python magic module. Args: query_string: a string of the form "[ALGO_HASH:]HASH" where optional ALGO_HASH can be either *sha1*, *sha1_git*, *sha256*, or *blake2s256* (default to *sha1*) and HASH the hexadecimal representation of the hash value max_size: the maximum size for a content to retrieve (default to 1MB, no size limit if None) Returns: A tuple whose first member corresponds to the content raw bytes and second member the content mime type Raises: NotFoundExc if the content is not found """ content_data = service.lookup_content(query_string) filetype = service.lookup_content_filetype(query_string) language = service.lookup_content_language(query_string) license = service.lookup_content_license(query_string) mimetype = 'unknown' encoding = 'unknown' if filetype: mimetype = filetype['mimetype'] encoding = filetype['encoding'] if not max_size or content_data['length'] < max_size: content_raw = service.lookup_content_raw(query_string) content_data['raw_data'] = content_raw['data'] if not filetype: mimetype, encoding = \ get_mimetype_and_encoding_for_content(content_data['raw_data']) # encode textual content to utf-8 if needed if mimetype.startswith('text/'): # probably a malformed UTF-8 content, reencode it # by replacing invalid chars with a substitution one if encoding == 'unknown-8bit': content_data['raw_data'] = \ content_data['raw_data'].decode('utf-8', 'replace')\ .encode('utf-8') elif 'ascii' not in encoding and encoding not in ['utf-8', 'binary']: # noqa content_data['raw_data'] = \ content_data['raw_data'].decode(encoding, 'replace')\ .encode('utf-8') else: content_data['raw_data'] = None content_data['mimetype'] = mimetype content_data['encoding'] = encoding if language: content_data['language'] = language['lang'] else: content_data['language'] = 'not detected' if license: content_data['licenses'] = ', '.join(license['licenses']) else: content_data['licenses'] = 'not detected' return content_data _browsers_supported_image_mimes = set(['image/gif', 'image/png', 'image/jpeg', 'image/bmp', 'image/webp']) def prepare_content_for_display(content_data, mime_type, path): """Function that prepares a content for HTML display. The function tries to associate a programming language to a content in order to perform syntax highlighting client-side using highlightjs. The language is determined using either the content filename or its mime type. If the mime type corresponds to an image format supported by web browsers, the content will be encoded in base64 for displaying the image. Args: content_data (bytes): raw bytes of the content mime_type (string): mime type of the content path (string): path of the content including filename Returns: A dict containing the content bytes (possibly different from the one provided as parameter if it is an image) under the key 'content_data and the corresponding highlightjs language class under the key 'language'. """ language = highlightjs.get_hljs_language_from_filename(path) if not language: language = highlightjs.get_hljs_language_from_mime_type(mime_type) if not language: language = 'nohighlight-swh' elif mime_type.startswith('application/'): mime_type = mime_type.replace('application/', 'text/') if mime_type.startswith('image/'): if mime_type in _browsers_supported_image_mimes: content_data = base64.b64encode(content_data) else: content_data = None return {'content_data': content_data, 'language': language} def get_origin_visits(origin_info): """Function that returns the list of visits for a swh origin. That list is put in cache in order to speedup the navigation in the swh web browse ui. Args: origin_id (int): the id of the swh origin to fetch visits from Returns: A list of dict describing the origin visits:: [{'date': , 'origin': , 'status': <'full' | 'partial'>, 'visit': }, ... ] Raises: NotFoundExc if the origin is not found """ cache_entry_id = 'origin_%s_visits' % origin_info['id'] cache_entry = cache.get(cache_entry_id) if cache_entry: return cache_entry origin_visits = [] per_page = service.MAX_LIMIT last_visit = None while 1: visits = list(service.lookup_origin_visits(origin_info['id'], last_visit=last_visit, per_page=per_page)) origin_visits += visits if len(visits) < per_page: break else: if not last_visit: last_visit = per_page else: last_visit += per_page def _visit_sort_key(visit): ts = parse_timestamp(visit['date']).timestamp() return ts + (float(visit['visit']) / 10e3) for v in origin_visits: if 'metadata' in v: del v['metadata'] origin_visits = [dict(t) for t in set([tuple(d.items()) for d in origin_visits])] origin_visits = sorted(origin_visits, key=lambda v: _visit_sort_key(v)) cache.set(cache_entry_id, origin_visits) return origin_visits def get_origin_visit(origin_info, visit_ts=None, visit_id=None): """Function that returns information about a SWH visit for a given origin. The visit is retrieved from a provided timestamp. The closest visit from that timestamp is selected. Args: origin_info (dict): a dict filled with origin information (id, url, type) visit_ts (int or str): an ISO date string or Unix timestamp to parse Returns: A dict containing the visit info as described below:: {'origin': 2, 'date': '2017-10-08T11:54:25.582463+00:00', 'metadata': {}, 'visit': 25, 'status': 'full'} """ visits = get_origin_visits(origin_info) if not visits: raise NotFoundExc('No SWH visit associated to origin with' ' type %s and url %s!' % (origin_info['type'], origin_info['url'])) if visit_id: visit = [v for v in visits if v['visit'] == int(visit_id)] if len(visit) == 0: raise NotFoundExc( 'Visit with id %s for origin with type %s' ' and url %s not found!' % (visit_id, origin_info['type'], origin_info['url'])) return visit[0] if not visit_ts: # returns the latest full visit when no timestamp is provided for v in reversed(visits): if v['status'] == 'full': return v return visits[-1] parsed_visit_ts = math.floor(parse_timestamp(visit_ts).timestamp()) visit_idx = None for i, visit in enumerate(visits): ts = math.floor(parse_timestamp(visit['date']).timestamp()) if i == 0 and parsed_visit_ts <= ts: return visit elif i == len(visits) - 1: if parsed_visit_ts >= ts: return visit else: next_ts = math.floor( parse_timestamp(visits[i+1]['date']).timestamp()) if parsed_visit_ts >= ts and parsed_visit_ts < next_ts: if (parsed_visit_ts - ts) < (next_ts - parsed_visit_ts): visit_idx = i break else: visit_idx = i+1 break if visit_idx: visit = visits[visit_idx] while visit_idx < len(visits) - 1 and \ visit['date'] == visits[visit_idx+1]['date']: visit_idx = visit_idx + 1 visit = visits[visit_idx] return visit else: raise NotFoundExc( 'Visit with timestamp %s for origin with type %s and url %s not found!' % # noqa (visit_ts, origin_info['type'], origin_info['url'])) def get_snapshot_content(snapshot_id): """Returns the lists of branches and releases associated to a swh snapshot. That list is put in cache in order to speedup the navigation in the swh-web/browse ui. Args: snapshot_id (str): hexadecimal representation of the snapshot identifier Returns: A tuple with two members. The first one is a list of dict describing the snapshot branches. The second one is a list of dict describing the snapshot releases. Raises: NotFoundExc if the snapshot does not exist """ cache_entry_id = 'swh_snapshot_%s' % snapshot_id cache_entry = cache.get(cache_entry_id) if cache_entry: return cache_entry['branches'], cache_entry['releases'] branches = [] releases = [] if snapshot_id: revision_ids = [] releases_ids = [] snapshot = service.lookup_snapshot(snapshot_id) snapshot_branches = snapshot['branches'] for key in sorted(snapshot_branches.keys()): if not snapshot_branches[key]: continue if snapshot_branches[key]['target_type'] == 'revision': branches.append({'name': key, 'revision': snapshot_branches[key]['target']}) revision_ids.append(snapshot_branches[key]['target']) elif snapshot_branches[key]['target_type'] == 'release': releases_ids.append(snapshot_branches[key]['target']) releases_info = service.lookup_release_multiple(releases_ids) for release in releases_info: releases.append({'name': release['name'], 'date': format_utc_iso_date(release['date']), 'id': release['id'], 'message': release['message'], 'target_type': release['target_type'], 'target': release['target']}) revision_ids.append(release['target']) revisions = service.lookup_revision_multiple(revision_ids) branches_to_remove = [] for idx, revision in enumerate(revisions): if idx < len(branches): if revision: branches[idx]['directory'] = revision['directory'] branches[idx]['date'] = format_utc_iso_date(revision['date']) # noqa branches[idx]['message'] = revision['message'] else: branches_to_remove.append(branches[idx]) else: rel_idx = idx - len(branches) if revision: releases[rel_idx]['directory'] = revision['directory'] for b in branches_to_remove: branches.remove(b) cache.set(cache_entry_id, {'branches': branches, 'releases': releases}) return branches, releases def get_origin_visit_snapshot(origin_info, visit_ts=None, visit_id=None): """Returns the lists of branches and releases associated to a swh origin for a given visit. The visit is expressed by a timestamp. In the latter case, the closest visit from the provided timestamp will be used. If no visit parameter is provided, it returns the list of branches found for the latest visit. That list is put in cache in order to speedup the navigation in the swh-web/browse ui. Args: origin_info (dict): a dict filled with origin information (id, url, type) visit_ts (int or str): an ISO date string or Unix timestamp to parse visit_id (int): optional visit id for desambiguation in case several visits have the same timestamp Returns: A tuple with two members. The first one is a list of dict describing the origin branches for the given visit. The second one is a list of dict describing the origin releases for the given visit. Raises: NotFoundExc if the origin or its visit are not found """ visit_info = get_origin_visit(origin_info, visit_ts, visit_id) return get_snapshot_content(visit_info['snapshot']) def gen_link(url, link_text, link_attrs={}): """ Utility function for generating an HTML link to insert in Django templates. Args: url (str): an url link_text (str): the text for the produced link link_attrs (dict): optional attributes (e.g. class) to add to the link Returns: An HTML link in the form 'link_text' """ attrs = ' ' for k, v in link_attrs.items(): attrs += '%s="%s" ' % (k, v) link = '%s' % (attrs, url, link_text) return mark_safe(link) def gen_person_link(person_id, person_name, link_attrs={}): """ Utility function for generating a link to a SWH person HTML view to insert in Django templates. Args: person_id (int): a SWH person id person_name (str): the associated person name link_attrs (dict): optional attributes (e.g. class) to add to the link Returns: An HTML link in the form 'person_name' """ person_url = reverse('browse-person', kwargs={'person_id': person_id}) return gen_link(person_url, person_name, link_attrs) def gen_revision_link(revision_id, shorten_id=False, snapshot_context=None, link_text=None, link_attrs={}): """ Utility function for generating a link to a SWH revision HTML view to insert in Django templates. Args: revision_id (str): a SWH revision id shorten_id (boolean): wheter to shorten the revision id to 7 characters for the link text snapshot_context (dict): if provided, generate snapshot-dependent browsing link link_attrs (dict): optional attributes (e.g. class) to add to the link Returns: An HTML link in the form 'revision_id' """ query_params = None if snapshot_context and snapshot_context['origin_info']: origin_info = snapshot_context['origin_info'] query_params = {'origin_type': origin_info['type'], 'origin_url': origin_info['url']} if 'timestamp' in snapshot_context['url_args']: query_params['timestamp'] = \ snapshot_context['url_args']['timestamp'] if 'visit_id' in snapshot_context['query_params']: query_params['visit_id'] = \ snapshot_context['query_params']['visit_id'] elif snapshot_context: query_params = {'snapshot_id': snapshot_context['snapshot_id']} revision_url = reverse('browse-revision', kwargs={'sha1_git': revision_id}, query_params=query_params) if shorten_id: return gen_link(revision_url, revision_id[:7], link_attrs) else: if not link_text: link_text = revision_id return gen_link(revision_url, link_text, link_attrs) def gen_origin_link(origin_info, link_attrs={}): """ Utility function for generating a link to a SWH origin HTML view to insert in Django templates. Args: origin_info (dict): a dicted filled with origin information (id, type, url) link_attrs (dict): optional attributes (e.g. class) to add to the link Returns: An HTML link in the form 'Origin: origin_url' """ # noqa origin_browse_url = reverse('browse-origin', kwargs={'origin_type': origin_info['type'], 'origin_url': origin_info['url']}) return gen_link(origin_browse_url, 'Origin: ' + origin_info['url'], link_attrs) def gen_directory_link(sha1_git, link_text=None, link_attrs={}): """ Utility function for generating a link to a SWH directory HTML view to insert in Django templates. Args: sha1_git (str): directory identifier link_text (str): optional text for the generated link (the generated url will be used by default) link_attrs (dict): optional attributes (e.g. class) to add to the link Returns: An HTML link in the form 'link_text' """ directory_url = reverse('browse-directory', kwargs={'sha1_git': sha1_git}) if not link_text: link_text = directory_url return gen_link(directory_url, link_text, link_attrs) def gen_snapshot_link(snapshot_id, link_text=None, link_attrs={}): """ Utility function for generating a link to a SWH snapshot HTML view to insert in Django templates. Args: snapshot_id (str): snapshot identifier link_text (str): optional text for the generated link (the generated url will be used by default) link_attrs (dict): optional attributes (e.g. class) to add to the link Returns: An HTML link in the form 'link_text' """ snapshot_url = reverse('browse-snapshot', kwargs={'snapshot_id': snapshot_id}) if not link_text: link_text = snapshot_url return gen_link(snapshot_url, link_text, link_attrs) def gen_snapshot_directory_link(snapshot_context, revision_id=None, link_text=None, link_attrs={}): """ Utility function for generating a link to a SWH directory HTML view in the context of a snapshot to insert in Django templates. Args: snapshot_context (dict): the snapshot information revision_id (str): optional revision identifier in order to use the associated directory link_text (str): optional text to use for the generated link link_attrs (dict): optional attributes (e.g. class) to add to the link Returns: An HTML link in the form 'origin_directory_view_url' """ query_params = {'revision': revision_id} if snapshot_context['origin_info']: origin_info = snapshot_context['origin_info'] url_args = {'origin_type': origin_info['type'], 'origin_url': origin_info['url']} if 'timestamp' in snapshot_context['url_args']: url_args['timestamp'] = \ snapshot_context['url_args']['timestamp'] if 'visit_id' in snapshot_context['query_params']: query_params['visit_id'] = \ snapshot_context['query_params']['visit_id'] directory_url = reverse('browse-origin-directory', kwargs=url_args, query_params=query_params) else: url_args = {'snapshot_id': snapshot_context['snapshot_id']} directory_url = reverse('browse-snapshot-directory', kwargs=url_args, query_params=query_params) if not link_text: link_text = directory_url return gen_link(directory_url, link_text, link_attrs) def gen_content_link(sha1_git, link_text=None, link_attrs={}): """ Utility function for generating a link to a SWH content HTML view to insert in Django templates. Args: sha1_git (str): content identifier link_text (str): optional text for the generated link (the generated url will be used by default) link_attrs (dict): optional attributes (e.g. class) to add to the link Returns: An HTML link in the form 'link_text' """ content_url = reverse('browse-content', kwargs={'query_string': 'sha1_git:' + sha1_git}) if not link_text: link_text = content_url return gen_link(content_url, link_text, link_attrs) def get_revision_log_url(revision_id, snapshot_context=None): """ Utility function for getting the URL for a SWH revision log HTML view (possibly in the context of an origin). Args: revision_id (str): revision identifier the history heads to snapshot_context (dict): if provided, generate snapshot-dependent browsing link Returns: The SWH revision log view URL """ query_params = {'revision': revision_id} if snapshot_context and snapshot_context['origin_info']: origin_info = snapshot_context['origin_info'] url_args = {'origin_type': origin_info['type'], 'origin_url': origin_info['url']} if 'timestamp' in snapshot_context['url_args']: url_args['timestamp'] = \ snapshot_context['url_args']['timestamp'] if 'visit_id' in snapshot_context['query_params']: query_params['visit_id'] = \ snapshot_context['query_params']['visit_id'] revision_log_url = reverse('browse-origin-log', kwargs=url_args, query_params=query_params) elif snapshot_context: url_args = {'snapshot_id': snapshot_context['snapshot_id']} revision_log_url = reverse('browse-snapshot-log', kwargs=url_args, query_params=query_params) else: revision_log_url = reverse('browse-revision-log', kwargs={'sha1_git': revision_id}) return revision_log_url def gen_revision_log_link(revision_id, snapshot_context=None, link_text=None, link_attrs={}): """ Utility function for generating a link to a SWH revision log HTML view (possibly in the context of an origin) to insert in Django templates. Args: revision_id (str): revision identifier the history heads to snapshot_context (dict): if provided, generate snapshot-dependent browsing link link_text (str): optional text to use for the generated link link_attrs (dict): optional attributes (e.g. class) to add to the link Returns: An HTML link in the form 'link_text' """ revision_log_url = get_revision_log_url(revision_id, snapshot_context) if not link_text: link_text = revision_log_url return gen_link(revision_log_url, link_text, link_attrs) def _format_log_entries(revision_log, per_page, snapshot_context=None): revision_log_data = [] for i, log in enumerate(revision_log): if i == per_page: break revision_log_data.append( {'author': gen_person_link(log['author']['id'], log['author']['name']), 'revision': gen_revision_link(log['id'], True, snapshot_context), 'message': log['message'], 'date': format_utc_iso_date(log['date']), 'directory': log['directory']}) return revision_log_data def prepare_revision_log_for_display(revision_log, per_page, revs_breadcrumb, snapshot_context=None): """ Utility functions that process raw revision log data for HTML display. Its purpose is to: * add links to relevant SWH browse views * format date in human readable format * truncate the message log It also computes the data needed to generate the links for navigating back and forth in the history log. Args: revision_log (list): raw revision log as returned by the SWH web api per_page (int): number of log entries per page revs_breadcrumb (str): breadcrumbs of revisions navigated so far, in the form 'rev1[/rev2/../revN]'. Each revision corresponds to the first one displayed in the HTML view for history log. snapshot_context (dict): if provided, generate snapshot-dependent browsing link """ current_rev = revision_log[0]['id'] next_rev = None prev_rev = None next_revs_breadcrumb = None prev_revs_breadcrumb = None if len(revision_log) == per_page + 1: prev_rev = revision_log[-1]['id'] prev_rev_bc = current_rev if snapshot_context: prev_rev_bc = prev_rev if revs_breadcrumb: revs = revs_breadcrumb.split('/') next_rev = revs[-1] if len(revs) > 1: next_revs_breadcrumb = '/'.join(revs[:-1]) if len(revision_log) == per_page + 1: prev_revs_breadcrumb = revs_breadcrumb + '/' + prev_rev_bc else: prev_revs_breadcrumb = prev_rev_bc return {'revision_log_data': _format_log_entries(revision_log, per_page, snapshot_context), 'prev_rev': prev_rev, 'prev_revs_breadcrumb': prev_revs_breadcrumb, 'next_rev': next_rev, 'next_revs_breadcrumb': next_revs_breadcrumb} +# list of origin types that can be found in the swh archive +# TODO: retrieve it dynamically in an efficient way instead +# of hardcoding it +_swh_origin_types = ['git', 'svn', 'deb', 'hg', 'ftp', 'deposit'] + + +def get_origin_info(origin_url, origin_type=None): + """ + Get info about a SWH origin. + Its main purpose is to automatically find an origin type + when it is not provided as parameter. + + Args: + origin_url (str): complete url of a SWH origin + origin_type (str): optionnal origin type + + Returns: + A dict with the following entries: + * type: the origin type + * url: the origin url + * id: the SWH internal id of the origin + """ + if origin_type: + return service.lookup_origin({'type': origin_type, + 'url': origin_url}) + else: + for origin_type in _swh_origin_types: + origin_info = service.lookup_origin({'type': origin_type, + 'url': origin_url}) + if origin_info: + return origin_info + return None + + def get_snapshot_context(snapshot_id=None, origin_type=None, origin_url=None, timestamp=None, visit_id=None): """ Utility function to compute relevant information when navigating the SWH archive in a snapshot context. The snapshot is either referenced by its id or it will be retrieved from an origin visit. Args: snapshot_id (str): hexadecimal representation of a snapshot identifier, all other parameters will be ignored if it is provided origin_type (str): the origin type (git, svn, deposit, ...) origin_url (str): the origin_url (e.g. https://github.com/(user)/(repo)/) timestamp (str): a datetime string for retrieving the closest SWH visit of the origin visit_id (int): optional visit id for disambiguation in case of several visits with the same timestamp Returns: A dict with the following entries: * origin_info: dict containing origin information * visit_info: dict containing SWH visit information * branches: the list of branches for the origin found during the visit * releases: the list of releases for the origin found during the visit * origin_browse_url: the url to browse the origin * origin_branches_url: the url to browse the origin branches * origin_releases_url': the url to browse the origin releases * origin_visit_url: the url to browse the snapshot of the origin found during the visit * url_args: dict containg url arguments to use when browsing in the context of the origin and its visit """ # noqa origin_info = None visit_info = None url_args = None query_params = {} branches = [] releases = [] browse_url = None visit_url = None branches_url = None releases_url = None swh_type = 'snapshot' - if origin_type and origin_url: + if origin_url: swh_type = 'origin' - origin_info = service.lookup_origin({'type': origin_type, - 'url': origin_url}) + origin_info = get_origin_info(origin_url, origin_type) + origin_info['type'] = origin_type visit_info = get_origin_visit(origin_info, timestamp, visit_id) visit_info['fmt_date'] = format_utc_iso_date(visit_info['date']) snapshot_id = visit_info['snapshot'] # provided timestamp is not necessarily equals to the one # of the retrieved visit, so get the exact one in order # use it in the urls generated below if timestamp: timestamp = visit_info['date'] branches, releases = \ get_origin_visit_snapshot(origin_info, timestamp, visit_id) url_args = {'origin_type': origin_info['type'], 'origin_url': origin_info['url']} query_params = {'visit_id': visit_id} browse_url = reverse('browse-origin-visits', kwargs=url_args) if timestamp: url_args['timestamp'] = format_utc_iso_date(timestamp, '%Y-%m-%dT%H:%M:%S') visit_url = reverse('browse-origin-directory', kwargs=url_args, query_params=query_params) visit_info['url'] = visit_url branches_url = reverse('browse-origin-branches', kwargs=url_args, query_params=query_params) releases_url = reverse('browse-origin-releases', kwargs=url_args, query_params=query_params) elif snapshot_id: branches, releases = get_snapshot_content(snapshot_id) url_args = {'snapshot_id': snapshot_id} browse_url = reverse('browse-snapshot', kwargs=url_args) branches_url = reverse('browse-snapshot-branches', kwargs=url_args) releases_url = reverse('browse-snapshot-releases', kwargs=url_args) releases = list(reversed(releases)) return { 'swh_type': swh_type, 'snapshot_id': snapshot_id, 'origin_info': origin_info, 'visit_info': visit_info, 'branches': branches, 'releases': releases, 'branch': None, 'release': None, 'browse_url': browse_url, 'branches_url': branches_url, 'releases_url': releases_url, 'url_args': url_args, 'query_params': query_params } diff --git a/swh/web/browse/views/origin.py b/swh/web/browse/views/origin.py index 5f0789c2..9fcd1f96 100644 --- a/swh/web/browse/views/origin.py +++ b/swh/web/browse/views/origin.py @@ -1,225 +1,238 @@ # Copyright (C) 2017-2018 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU Affero General Public License version 3, or any later version # See top-level LICENSE file for more information import json from distutils.util import strtobool from django.http import HttpResponse from django.shortcuts import render, redirect from swh.web.common import service from swh.web.common.utils import ( reverse, format_utc_iso_date, parse_timestamp ) from swh.web.common.exc import handle_view_exception -from swh.web.browse.utils import get_origin_visits +from swh.web.browse.utils import ( + get_origin_info, get_origin_visits +) from swh.web.browse.browseurls import browse_route from .utils.snapshot_context import ( browse_snapshot_directory, browse_snapshot_content, browse_snapshot_log, browse_snapshot_branches, browse_snapshot_releases ) @browse_route(r'origin/(?P[a-z]+)/url/(?P.+)/visit/(?P.+)/directory/', # noqa r'origin/(?P[a-z]+)/url/(?P.+)/visit/(?P.+)/directory/(?P.+)/', # noqa r'origin/(?P[a-z]+)/url/(?P.+)/directory/', # noqa r'origin/(?P[a-z]+)/url/(?P.+)/directory/(?P.+)/', # noqa + r'origin/(?P.+)/visit/(?P.+)/directory/', # noqa + r'origin/(?P.+)/visit/(?P.+)/directory/(?P.+)/', # noqa + r'origin/(?P.+)/directory/', # noqa + r'origin/(?P.+)/directory/(?P.+)/', # noqa view_name='browse-origin-directory') -def origin_directory_browse(request, origin_type, origin_url, +def origin_directory_browse(request, origin_url, origin_type=None, timestamp=None, path=None): """Django view for browsing the content of a SWH directory associated to an origin for a given visit. The url scheme that points to it is the following: - * :http:get:`/browse/origin/(origin_type)/url/(origin_url)/directory/[(path)/]` - * :http:get:`/browse/origin/(origin_type)/url/(origin_url)/visit/(timestamp)/directory/[(path)/]` + * :http:get:`/browse/origin/[(origin_type)/url/](origin_url)/directory/[(path)/]` + * :http:get:`/browse/origin/[(origin_type)/url/](origin_url)/visit/(timestamp)/directory/[(path)/]` """ # noqa return browse_snapshot_directory( request, origin_type=origin_type, origin_url=origin_url, timestamp=timestamp, path=path) @browse_route(r'origin/(?P[a-z]+)/url/(?P.+)/visit/(?P.+)/content/(?P.+)/', # noqa r'origin/(?P[a-z]+)/url/(?P.+)/content/(?P.+)/', # noqa + r'origin/(?P.+)/visit/(?P.+)/content/(?P.+)/', # noqa + r'origin/(?P.+)/content/(?P.+)/', # noqa view_name='browse-origin-content') -def origin_content_browse(request, origin_type, origin_url, path, +def origin_content_browse(request, origin_url, origin_type=None, path=None, timestamp=None): """Django view that produces an HTML display of a SWH content associated to an origin for a given visit. The url scheme that points to it is the following: - * :http:get:`/browse/origin/(origin_type)/url/(origin_url)/content/(path)/` - * :http:get:`/browse/origin/(origin_type)/url/(origin_url)/visit/(timestamp)/content/(path)/` + * :http:get:`/browse/origin/[(origin_type)/url/](origin_url)/content/(path)/` + * :http:get:`/browse/origin/[(origin_type)/url/](origin_url)/visit/(timestamp)/content/(path)/` """ # noqa return browse_snapshot_content(request, origin_type=origin_type, origin_url=origin_url, timestamp=timestamp, path=path) PER_PAGE = 20 @browse_route(r'origin/(?P[a-z]+)/url/(?P.+)/visit/(?P.+)/log/', # noqa r'origin/(?P[a-z]+)/url/(?P.+)/log/', + r'origin/(?P.+)/visit/(?P.+)/log/', # noqa + r'origin/(?P.+)/log/', view_name='browse-origin-log') -def origin_log_browse(request, origin_type, origin_url, timestamp=None): +def origin_log_browse(request, origin_url, origin_type=None, timestamp=None): """Django view that produces an HTML display of revisions history (aka the commit log) associated to a SWH origin. The url scheme that points to it is the following: - * :http:get:`/browse/origin/(origin_type)/url/(origin_url)/log/` - * :http:get:`/browse/origin/(origin_type)/url/(origin_url)/visit/(timestamp)/log/` + * :http:get:`/browse/origin/[(origin_type)/url/](origin_url)/log/` + * :http:get:`/browse/origin/[(origin_type)/url/](origin_url)/visit/(timestamp)/log/` """ # noqa return browse_snapshot_log(request, origin_type=origin_type, origin_url=origin_url, timestamp=timestamp) @browse_route(r'origin/(?P[a-z]+)/url/(?P.+)/visit/(?P.+)/branches/', # noqa r'origin/(?P[a-z]+)/url/(?P.+)/branches/', # noqa + r'origin/(?P.+)/visit/(?P.+)/branches/', # noqa + r'origin/(?P.+)/branches/', # noqa view_name='browse-origin-branches') -def origin_branches_browse(request, origin_type, origin_url, timestamp=None): +def origin_branches_browse(request, origin_url, origin_type=None, + timestamp=None): """Django view that produces an HTML display of the list of branches associated to an origin for a given visit. The url scheme that points to it is the following: - * :http:get:`/browse/origin/(origin_type)/url/(origin_url)/branches/` - * :http:get:`/browse/origin/(origin_type)/url/(origin_url)/visit/(timestamp)/branches/` + * :http:get:`/browse/origin/[(origin_type)/url/](origin_url)/branches/` + * :http:get:`/browse/origin/[(origin_type)/url/](origin_url)/visit/(timestamp)/branches/` """ # noqa return browse_snapshot_branches(request, origin_type=origin_type, origin_url=origin_url, timestamp=timestamp) @browse_route(r'origin/(?P[a-z]+)/url/(?P.+)/visit/(?P.+)/releases/', # noqa r'origin/(?P[a-z]+)/url/(?P.+)/releases/', # noqa + r'origin/(?P.+)/visit/(?P.+)/releases/', # noqa + r'origin/(?P.+)/releases/', # noqa view_name='browse-origin-releases') -def origin_releases_browse(request, origin_type, origin_url, timestamp=None): +def origin_releases_browse(request, origin_url, origin_type=None, + timestamp=None): """Django view that produces an HTML display of the list of releases associated to an origin for a given visit. The url scheme that points to it is the following: - * :http:get:`/browse/origin/(origin_type)/url/(origin_url)/releases/` - * :http:get:`/browse/origin/(origin_type)/url/(origin_url)/visit/(timestamp)/releases/` + * :http:get:`/browse/origin/[(origin_type)/url/](origin_url)/releases/` + * :http:get:`/browse/origin/[(origin_type)/url/](origin_url)/visit/(timestamp)/releases/` """ # noqa return browse_snapshot_releases(request, origin_type=origin_type, origin_url=origin_url, timestamp=timestamp) @browse_route(r'origin/(?P[a-z]+)/url/(?P.+)/visits/', + r'origin/(?P.+)/visits/', view_name='browse-origin-visits') -def origin_visits_browse(request, origin_type=None, origin_url=None): +def origin_visits_browse(request, origin_url, origin_type=None): """Django view that produces an HTML display of visits reporting for a swh origin identified by its id or its url. - The url that points to it is :http:get:`/browse/origin/(origin_type)/url/(origin_url)/visits/`. + The url that points to it is :http:get:`/browse/origin/[(origin_type)/url/](origin_url)/visits/`. """ # noqa try: - origin_info = service.lookup_origin({ - 'type': origin_type, - 'url': origin_url - }) + origin_info = get_origin_info(origin_url, origin_type) origin_visits = get_origin_visits(origin_info) except Exception as exc: return handle_view_exception(request, exc) origin_info['last swh visit browse url'] = \ - reverse('browse-origin', - kwargs={'origin_type': origin_type, - 'origin_url': origin_url}) + reverse('browse-origin-directory', + kwargs={'origin_url': origin_url, + 'origin_type': origin_type}) for i, visit in enumerate(origin_visits): url_date = format_utc_iso_date(visit['date'], '%Y-%m-%dT%H:%M:%SZ') visit['fmt_date'] = format_utc_iso_date(visit['date']) query_params = {} if i < len(origin_visits) - 1: if visit['date'] == origin_visits[i+1]['date']: query_params = {'visit_id': visit['visit']} if i > 0: if visit['date'] == origin_visits[i-1]['date']: query_params = {'visit_id': visit['visit']} snapshot = visit['snapshot'] if visit['snapshot'] else '' visit['browse_url'] = reverse('browse-origin-directory', kwargs={'origin_type': origin_type, 'origin_url': origin_url, 'timestamp': url_date}, query_params=query_params) if not snapshot: visit['snapshot'] = '' visit['date'] = parse_timestamp(visit['date']).timestamp() return render(request, 'origin-visits.html', {'empty_browse': False, 'heading': 'Origin', 'top_panel_visible': False, 'top_panel_collapsible': False, 'top_panel_text': 'Origin visits', 'swh_object_metadata': origin_info, 'main_panel_visible': True, 'origin_visits': origin_visits, 'origin_info': origin_info, 'browse_url_base': '/browse/origin/%s/url/%s/' % (origin_type, origin_url), 'vault_cooking': None, 'show_actions_menu': False}) -@browse_route(r'origin/(?P[a-z]+)/url/(?P.+)/', - view_name='browse-origin') -def origin_browse(request, origin_type=None, origin_url=None): - """Django view that redirects to the display of the latest archived - snapshot for a given software origin. - - The url that points to it is :http:get:`/browse/origin/(origin_type)/url/(origin_url)/`. - """ # noqa - last_snapshot_url = reverse('browse-origin-directory', - kwargs={'origin_type': origin_type, - 'origin_url': origin_url}) - return redirect(last_snapshot_url) - - @browse_route(r'origin/search/(?P.+)/', view_name='browse-origin-search') def _origin_search(request, url_pattern): """Internal browse endpoint to search for origins whose urls contain a provided string pattern or match a provided regular expression. The search is performed in a case insensitive way. """ offset = int(request.GET.get('offset', '0')) limit = int(request.GET.get('limit', '50')) regexp = request.GET.get('regexp', 'false') results = service.search_origin(url_pattern, offset, limit, bool(strtobool(regexp))) results = json.dumps(list(results), sort_keys=True, indent=4, separators=(',', ': ')) return HttpResponse(results, content_type='application/json') @browse_route(r'origin/(?P[0-9]+)/latest_snapshot/', view_name='browse-origin-latest-snapshot') def _origin_latest_snapshot(request, origin_id): """ Internal browse endpoint used to check if an origin has already been visited by Software Heritage and has at least one full visit. """ result = service.lookup_latest_origin_snapshot(origin_id, allowed_statuses=['full']) result = json.dumps(result, sort_keys=True, indent=4, separators=(',', ': ')) return HttpResponse(result, content_type='application/json') + + +@browse_route(r'origin/(?P[a-z]+)/url/(?P.+)/', + r'origin/(?P.+)/', + view_name='browse-origin') +def origin_browse(request, origin_url, origin_type=None): + """Django view that redirects to the display of the latest archived + snapshot for a given software origin. + """ # noqa + last_snapshot_url = reverse('browse-origin-directory', + kwargs={'origin_type': origin_type, + 'origin_url': origin_url}) + return redirect(last_snapshot_url) diff --git a/swh/web/common/utils.py b/swh/web/common/utils.py index caea7b06..9ea969ef 100644 --- a/swh/web/common/utils.py +++ b/swh/web/common/utils.py @@ -1,184 +1,187 @@ # Copyright (C) 2017-2018 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU Affero General Public License version 3, or any later version # See top-level LICENSE file for more information import re from datetime import datetime, timezone from dateutil import parser as date_parser from dateutil import tz from swh.web.common.exc import BadInputExc from django.core import urlresolvers from django.http import QueryDict def reverse(viewname, args=None, kwargs=None, query_params=None, current_app=None, urlconf=None): """An override of django reverse function supporting query parameters. Args: viewname: the name of the django view from which to compute a url args: list of url arguments ordered according to their position it kwargs: dictionary of url arguments indexed by their names query_params: dictionary of query parameters to append to the reversed url current_app: the name of the django app tighted to the view urlconf: url configuration module Returns: The url of the requested view with processed arguments and query parameters """ + if kwargs: + kwargs = {k: v for k, v in kwargs.items() if v is not None} + url = urlresolvers.reverse( viewname, urlconf=urlconf, args=args, kwargs=kwargs, current_app=current_app) if query_params: query_params = {k: v for k, v in query_params.items() if v is not None} if query_params and len(query_params) > 0: query_dict = QueryDict('', mutable=True) for k in sorted(query_params.keys()): query_dict[k] = query_params[k] url += ('?' + query_dict.urlencode(safe='/')) return url def fmap(f, data): """Map f to data at each level. This must keep the origin data structure type: - map -> map - dict -> dict - list -> list - None -> None Args: f: function that expects one argument. data: data to traverse to apply the f function. list, map, dict or bare value. Returns: The same data-structure with modified values by the f function. """ if data is None: return data if isinstance(data, map): return map(lambda y: fmap(f, y), (x for x in data)) if isinstance(data, list): return [fmap(f, x) for x in data] if isinstance(data, dict): return {k: fmap(f, v) for (k, v) in data.items()} return f(data) def datetime_to_utc(date): """Returns datetime in UTC without timezone info Args: date (datetime.datetime): input datetime with timezone info Returns: datetime.datime: datetime in UTC without timezone info """ if date.tzinfo: return date.astimezone(tz.gettz('UTC')).replace(tzinfo=timezone.utc) else: return date def parse_timestamp(timestamp): """Given a time or timestamp (as string), parse the result as UTC datetime. Returns: a timezone-aware datetime representing the parsed value. None if the parsing fails. Samples: - 2016-01-12 - 2016-01-12T09:19:12+0100 - Today is January 1, 2047 at 8:21:00AM - 1452591542 """ if not timestamp: return None try: date = date_parser.parse(timestamp, ignoretz=False, fuzzy=True) return datetime_to_utc(date) except Exception: try: return datetime.utcfromtimestamp(float(timestamp)).replace( tzinfo=timezone.utc) except (ValueError, OverflowError) as e: raise BadInputExc(e) def shorten_path(path): """Shorten the given path: for each hash present, only return the first 8 characters followed by an ellipsis""" sha256_re = r'([0-9a-f]{8})[0-9a-z]{56}' sha1_re = r'([0-9a-f]{8})[0-9a-f]{32}' ret = re.sub(sha256_re, r'\1...', path) return re.sub(sha1_re, r'\1...', ret) def format_utc_iso_date(iso_date, fmt='%d %B %Y, %H:%M UTC'): """Turns a string reprensation of an ISO 8601 date string to UTC and format it into a more human readable one. For instance, from the following input string: '2017-05-04T13:27:13+02:00' the following one is returned: '04 May 2017, 11:27 UTC'. Custom format string may also be provided as parameter Args: iso_date (str): a string representation of an ISO 8601 date fmt (str): optional date formatting string Returns: A formatted string representation of the input iso date """ if not iso_date: return iso_date date = parse_timestamp(iso_date) return date.strftime(fmt) def gen_path_info(path): """Function to generate path data navigation for use with a breadcrumb in the swh web ui. For instance, from a path /folder1/folder2/folder3, it returns the following list:: [{'name': 'folder1', 'path': 'folder1'}, {'name': 'folder2', 'path': 'folder1/folder2'}, {'name': 'folder3', 'path': 'folder1/folder2/folder3'}] Args: path: a filesystem path Returns: A list of path data for navigation as illustrated above. """ path_info = [] if path: sub_paths = path.strip('/').split('/') path_from_root = '' for p in sub_paths: path_from_root += '/' + p path_info.append({'name': p, 'path': path_from_root.strip('/')}) return path_info diff --git a/swh/web/templates/browse-help.html b/swh/web/templates/browse-help.html index 0ac89518..3b0c513b 100644 --- a/swh/web/templates/browse-help.html +++ b/swh/web/templates/browse-help.html @@ -1,194 +1,194 @@ {% extends "browse-layout.html" %} {% comment %} Copyright (C) 2017-2018 The Software Heritage developers See the AUTHORS file at the top-level directory of this distribution License: GNU Affero General Public License version 3, or any later version See top-level LICENSE file for more information {% endcomment %} {% block browse-content %}

How to browse the Software Heritage archive ?

Overview

This web application aims to provide HTML views to easily navigate in the Software Heritage archive. This is an ongoing development and new features and improvements will be progressively added over the time.

URI scheme

The current URI scheme of that web application is described below and depends on the type of Software Heritage object to browse. Its exhaustive documentation can be consulted from the official Software Heritage development documentation

Context-independent browsing

Context-independent URLs provide information about objects (e.g., revisions, directories, contents, persons, …), independently of the contexts where they have been found (e.g., specific software origins, branches, commits, …).

Below are some examples of endpoints used to just render the corresponding information for user consumption:

Where hyperlinks are created when browsing these kind of endpoints, they always point to other context-independent browsing URLs.

Context-dependent browsing

Context-dependent URLs provide information about objects, limited to specific contexts where the objects have been found.

Currently, browsing the Software Heritage objects in the context of an origin is available. Below are some examples of such endpoints:

Search software origins to browse

In order to facilitate the browsing of the archive and generate relevant entry points to it, a search interface is available. Currently, it enables to search software origins from the URLs they were retrieved from. More search criteria will be added in the future.
{% endblock %} \ No newline at end of file diff --git a/swh/web/templates/directory.html b/swh/web/templates/directory.html index 2e1ec4d6..151d5520 100644 --- a/swh/web/templates/directory.html +++ b/swh/web/templates/directory.html @@ -1,23 +1,24 @@ {% extends "browse.html" %} {% comment %} Copyright (C) 2017-2018 The Software Heritage developers See the AUTHORS file at the top-level directory of this distribution License: GNU Affero General Public License version 3, or any later version See top-level LICENSE file for more information {% endcomment %} + {% block swh-browse-before-panels %} {% if snapshot_context %} {% include "includes/snapshot-context.html" %} {% endif %} {% endblock %} {% block swh-browse-main-panel-content %} {% include "includes/top-navigation.html" %} {% include "includes/directory-display.html" %} {% endblock %} {% block swh-browse-panels-group-end %} {% include "includes/readme-display.html" %} {% endblock %} diff --git a/swh/web/templates/includes/snapshot-context.html b/swh/web/templates/includes/snapshot-context.html index 29f2edba..cf97835e 100644 --- a/swh/web/templates/includes/snapshot-context.html +++ b/swh/web/templates/includes/snapshot-context.html @@ -1,43 +1,47 @@ {% comment %} Copyright (C) 2017-2018 The Software Heritage developers See the AUTHORS file at the top-level directory of this distribution License: GNU Affero General Public License version 3, or any later version See top-level LICENSE file for more information {% endcomment %}
{% if snapshot_context.origin_info %}
See visits
{% if snapshot_context.origin_info.url|slice:"0:4" == "http" %}
Go to origin
{% endif %} - + {% if snapshot_context.origin_info.type %} + + {% else %} + + {% endif %}

Origin: {{ snapshot_context.origin_info.url }}

 {% else %}

Snapshot: {{ snapshot_context.snapshot_id }}

 {% endif %}
diff --git a/swh/web/tests/browse/views/test_origin.py b/swh/web/tests/browse/views/test_origin.py index 6ed6272e..3aeffee6 100644 --- a/swh/web/tests/browse/views/test_origin.py +++ b/swh/web/tests/browse/views/test_origin.py @@ -1,710 +1,821 @@ # Copyright (C) 2017-2018 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU Affero General Public License version 3, or any later version # See top-level LICENSE file for more information # flake8: noqa from unittest.mock import patch from nose.tools import istest, nottest from django.test import TestCase from django.utils.html import escape from swh.web.common.exc import NotFoundExc from swh.web.common.utils import ( reverse, gen_path_info, format_utc_iso_date, parse_timestamp ) from swh.web.tests.testbase import SWHWebTestBase from .data.origin_test_data import ( origin_info_test_data, origin_visits_test_data, stub_content_origin_info, stub_content_origin_visit_id, stub_content_origin_visit_unix_ts, stub_content_origin_visit_iso_date, stub_content_origin_branch, stub_content_origin_visits, stub_content_origin_snapshot, stub_origin_info, stub_visit_id, stub_origin_visits, stub_origin_snapshot, stub_origin_root_directory_entries, stub_origin_master_branch, stub_origin_root_directory_sha1, stub_origin_sub_directory_path, stub_origin_sub_directory_entries, stub_visit_unix_ts, stub_visit_iso_date ) from .data.content_test_data import ( stub_content_root_dir, stub_content_text_data, stub_content_text_path ) +stub_origin_info_no_type = dict(stub_origin_info) +stub_origin_info_no_type['type'] = None class SwhBrowseOriginTest(SWHWebTestBase, TestCase): @patch('swh.web.browse.views.origin.get_origin_visits') @patch('swh.web.browse.views.origin.service') @istest def origin_browse(self, mock_service, mock_get_origin_visits): mock_service.lookup_origin.return_value = origin_info_test_data mock_get_origin_visits.return_value = origin_visits_test_data url = reverse('browse-origin-visits', kwargs={'origin_type': origin_info_test_data['type'], 'origin_url': origin_info_test_data['url']}) resp = self.client.get(url) self.assertEquals(resp.status_code, 200) self.assertTemplateUsed('origin-visits.html') self.assertContains(resp, '
%s
' % origin_info_test_data['type']) self.assertContains(resp, '
%s
' % (origin_info_test_data['url'], origin_info_test_data['url'])) + url = reverse('browse-origin-visits', + kwargs={'origin_url': origin_info_test_data['url']}) + resp = self.client.get(url) + + self.assertEquals(resp.status_code, 200) + self.assertTemplateUsed('origin-visits.html') + self.assertContains(resp, '
%s
' % origin_info_test_data['type']) + self.assertContains(resp, '
%s
' % + (origin_info_test_data['url'], + origin_info_test_data['url'])) + @nottest def origin_content_view_test(self, origin_info, origin_visits, origin_branches, origin_releases, origin_branch, root_dir_sha1, content_sha1, content_path, content_data, content_language, visit_id=None, timestamp=None): url_args = {'origin_type': origin_info['type'], 'origin_url': origin_info['url'], 'path': content_path} if not visit_id: visit_id = origin_visits[-1]['visit'] query_params = {} if timestamp: url_args['timestamp'] = timestamp if visit_id: query_params['visit_id'] = visit_id url = reverse('browse-origin-content', kwargs=url_args, query_params=query_params) resp = self.client.get(url) self.assertEquals(resp.status_code, 200) self.assertTemplateUsed('content.html') self.assertContains(resp, '' % content_language) self.assertContains(resp, escape(content_data)) split_path = content_path.split('/') filename = split_path[-1] path = content_path.replace(filename, '')[:-1] path_info = gen_path_info(path) del url_args['path'] if timestamp: url_args['timestamp'] = \ format_utc_iso_date(parse_timestamp(timestamp).isoformat(), '%Y-%m-%dT%H:%M:%S') root_dir_url = reverse('browse-origin-directory', kwargs=url_args, query_params=query_params) self.assertContains(resp, '
  • ', count=len(path_info)+1) self.assertContains(resp, '%s' % (root_dir_url, root_dir_sha1[:7])) for p in path_info: url_args['path'] = p['path'] dir_url = reverse('browse-origin-directory', kwargs=url_args, query_params=query_params) self.assertContains(resp, '%s' % (dir_url, p['name'])) self.assertContains(resp, '
  • %s
    • ' % filename) query_string = 'sha1_git:' + content_sha1 url_raw = reverse('browse-content-raw', kwargs={'query_string': query_string}, query_params={'filename': filename}) self.assertContains(resp, url_raw) del url_args['path'] origin_branches_url = \ reverse('browse-origin-branches', kwargs=url_args, query_params=query_params) self.assertContains(resp, 'Branches (%s)' % (origin_branches_url, len(origin_branches))) origin_releases_url = \ reverse('browse-origin-releases', kwargs=url_args, query_params=query_params) self.assertContains(resp, 'Releases (%s)' % (origin_releases_url, len(origin_releases))) self.assertContains(resp, '
  • ', count=len(origin_branches)) url_args['path'] = content_path for branch in origin_branches: query_params['branch'] = branch['name'] root_dir_branch_url = \ reverse('browse-origin-content', kwargs=url_args, query_params=query_params) self.assertContains(resp, '' % root_dir_branch_url) self.assertContains(resp, '
  • ', count=len(origin_releases)) query_params['branch'] = None for release in origin_releases: query_params['release'] = release['name'] root_dir_release_url = \ reverse('browse-origin-content', kwargs=url_args, query_params=query_params) self.assertContains(resp, '' % root_dir_release_url) + del url_args['origin_type'] + + url = reverse('browse-origin-content', + kwargs=url_args, + query_params=query_params) + + resp = self.client.get(url) + self.assertEquals(resp.status_code, 200) + self.assertTemplateUsed('content.html') + @patch('swh.web.browse.utils.get_origin_visits') @patch('swh.web.browse.utils.get_origin_visit_snapshot') @patch('swh.web.browse.views.utils.snapshot_context.service') @patch('swh.web.browse.utils.service') @patch('swh.web.browse.views.utils.snapshot_context.request_content') @istest def origin_content_view(self, mock_request_content, mock_utils_service, mock_service, mock_get_origin_visit_snapshot, mock_get_origin_visits): stub_content_text_sha1 = stub_content_text_data['checksums']['sha1'] mock_get_origin_visits.return_value = stub_content_origin_visits mock_get_origin_visit_snapshot.return_value = stub_content_origin_snapshot mock_service.lookup_directory_with_path.return_value = \ {'target': stub_content_text_sha1} mock_request_content.return_value = stub_content_text_data mock_utils_service.lookup_origin.return_value = stub_content_origin_info self.origin_content_view_test(stub_content_origin_info, stub_content_origin_visits, stub_content_origin_snapshot[0], stub_content_origin_snapshot[1], stub_content_origin_branch, stub_content_root_dir, stub_content_text_sha1, stub_content_text_path, stub_content_text_data['raw_data'], 'cpp') self.origin_content_view_test(stub_content_origin_info, stub_content_origin_visits, stub_content_origin_snapshot[0], stub_content_origin_snapshot[1], stub_content_origin_branch, stub_content_root_dir, stub_content_text_sha1, stub_content_text_path, stub_content_text_data['raw_data'], 'cpp', visit_id=stub_content_origin_visit_id) self.origin_content_view_test(stub_content_origin_info, stub_content_origin_visits, stub_content_origin_snapshot[0], stub_content_origin_snapshot[1], stub_content_origin_branch, stub_content_root_dir, stub_content_text_sha1, stub_content_text_path, stub_content_text_data['raw_data'], 'cpp', timestamp=stub_content_origin_visit_unix_ts) self.origin_content_view_test(stub_content_origin_info, stub_content_origin_visits, stub_content_origin_snapshot[0], stub_content_origin_snapshot[1], stub_content_origin_branch, stub_content_root_dir, stub_content_text_sha1, stub_content_text_path, stub_content_text_data['raw_data'], 'cpp', timestamp=stub_content_origin_visit_iso_date) @nottest def origin_directory_view(self, origin_info, origin_visits, origin_branches, origin_releases, origin_branch, root_directory_sha1, directory_entries, visit_id=None, timestamp=None, path=None): dirs = [e for e in directory_entries if e['type'] == 'dir'] files = [e for e in directory_entries if e['type'] == 'file'] if not visit_id: visit_id = origin_visits[-1]['visit'] url_args = {'origin_type': origin_info['type'], 'origin_url': origin_info['url']} query_params = {} if timestamp: url_args['timestamp'] = timestamp else: query_params['visit_id'] = visit_id if path: url_args['path'] = path url = reverse('browse-origin-directory', kwargs=url_args, query_params=query_params) resp = self.client.get(url) self.assertEquals(resp.status_code, 200) self.assertTemplateUsed('directory.html') + + self.assertEquals(resp.status_code, 200) + self.assertTemplateUsed('directory.html') + + self.assertContains(resp, '', count=len(dirs)) self.assertContains(resp, '', count=len(files)) if timestamp: url_args['timestamp'] = \ format_utc_iso_date(parse_timestamp(timestamp).isoformat(), '%Y-%m-%dT%H:%M:%S') for d in dirs: dir_path = d['name'] if path: dir_path = "%s/%s" % (path, d['name']) dir_url_args = dict(url_args) dir_url_args['path'] = dir_path dir_url = reverse('browse-origin-directory', kwargs=dir_url_args, query_params=query_params) self.assertContains(resp, dir_url) for f in files: file_path = f['name'] if path: file_path = "%s/%s" % (path, f['name']) file_url_args = dict(url_args) file_url_args['path'] = file_path file_url = reverse('browse-origin-content', kwargs=file_url_args, query_params=query_params) self.assertContains(resp, file_url) if 'path' in url_args: del url_args['path'] root_dir_branch_url = \ reverse('browse-origin-directory', kwargs=url_args, query_params=query_params) nb_bc_paths = 1 if path: nb_bc_paths = len(path.split('/')) + 1 self.assertContains(resp, '
  • ', count=nb_bc_paths) self.assertContains(resp, '%s' % (root_dir_branch_url, root_directory_sha1[:7])) origin_branches_url = \ reverse('browse-origin-branches', kwargs=url_args, query_params=query_params) self.assertContains(resp, 'Branches (%s)' % (origin_branches_url, len(origin_branches))) origin_releases_url = \ reverse('browse-origin-releases', kwargs=url_args, query_params=query_params) self.assertContains(resp, 'Releases (%s)' % (origin_releases_url, len(origin_releases))) if path: url_args['path'] = path self.assertContains(resp, '
  • ', count=len(origin_branches)) for branch in origin_branches: query_params['branch'] = branch['name'] root_dir_branch_url = \ reverse('browse-origin-directory', kwargs=url_args, query_params=query_params) self.assertContains(resp, '' % root_dir_branch_url) self.assertContains(resp, '
  • ', count=len(origin_releases)) query_params['branch'] = None for release in origin_releases: query_params['release'] = release['name'] root_dir_release_url = \ reverse('browse-origin-directory', kwargs=url_args, query_params=query_params) self.assertContains(resp, '' % root_dir_release_url) self.assertContains(resp, 'vault-cook-directory') self.assertContains(resp, 'vault-cook-revision') + @patch('swh.web.browse.utils.get_origin_visits') @patch('swh.web.browse.utils.get_origin_visit_snapshot') @patch('swh.web.browse.utils.service') @patch('swh.web.browse.views.origin.service') @istest - def origin_root_directory_view(self, mock_origin_service, + def test_origin_root_directory_view(self, mock_origin_service, mock_utils_service, mock_get_origin_visit_snapshot, mock_get_origin_visits): mock_get_origin_visits.return_value = stub_origin_visits mock_get_origin_visit_snapshot.return_value = stub_origin_snapshot mock_utils_service.lookup_directory.return_value = \ stub_origin_root_directory_entries mock_utils_service.lookup_origin.return_value = stub_origin_info self.origin_directory_view(stub_origin_info, stub_origin_visits, stub_origin_snapshot[0], stub_origin_snapshot[1], stub_origin_master_branch, stub_origin_root_directory_sha1, stub_origin_root_directory_entries) self.origin_directory_view(stub_origin_info, stub_origin_visits, stub_origin_snapshot[0], stub_origin_snapshot[1], stub_origin_master_branch, stub_origin_root_directory_sha1, stub_origin_root_directory_entries, visit_id=stub_visit_id) self.origin_directory_view(stub_origin_info, stub_origin_visits, stub_origin_snapshot[0], stub_origin_snapshot[1], stub_origin_master_branch, stub_origin_root_directory_sha1, stub_origin_root_directory_entries, timestamp=stub_visit_unix_ts) self.origin_directory_view(stub_origin_info, stub_origin_visits, stub_origin_snapshot[0], stub_origin_snapshot[1], stub_origin_master_branch, stub_origin_root_directory_sha1, stub_origin_root_directory_entries, timestamp=stub_visit_iso_date) + self.origin_directory_view(stub_origin_info_no_type, stub_origin_visits, + stub_origin_snapshot[0], + stub_origin_snapshot[1], + stub_origin_master_branch, + stub_origin_root_directory_sha1, + stub_origin_root_directory_entries) + + self.origin_directory_view(stub_origin_info_no_type, stub_origin_visits, + stub_origin_snapshot[0], + stub_origin_snapshot[1], + stub_origin_master_branch, + stub_origin_root_directory_sha1, + stub_origin_root_directory_entries, + visit_id=stub_visit_id) + + self.origin_directory_view(stub_origin_info_no_type, stub_origin_visits, + stub_origin_snapshot[0], + stub_origin_snapshot[1], + stub_origin_master_branch, + stub_origin_root_directory_sha1, + stub_origin_root_directory_entries, + timestamp=stub_visit_unix_ts) + + self.origin_directory_view(stub_origin_info_no_type, stub_origin_visits, + stub_origin_snapshot[0], + stub_origin_snapshot[1], + stub_origin_master_branch, + stub_origin_root_directory_sha1, + stub_origin_root_directory_entries, + timestamp=stub_visit_iso_date) + @patch('swh.web.browse.utils.get_origin_visits') @patch('swh.web.browse.utils.get_origin_visit_snapshot') @patch('swh.web.browse.utils.service') @patch('swh.web.browse.views.utils.snapshot_context.service') @istest def origin_sub_directory_view(self, mock_origin_service, mock_utils_service, mock_get_origin_visit_snapshot, mock_get_origin_visits): mock_get_origin_visits.return_value = stub_origin_visits mock_get_origin_visit_snapshot.return_value = stub_origin_snapshot mock_utils_service.lookup_directory.return_value = \ stub_origin_sub_directory_entries mock_origin_service.lookup_directory_with_path.return_value = \ {'target': '120c39eeb566c66a77ce0e904d29dfde42228adb'} mock_utils_service.lookup_origin.return_value = stub_origin_info self.origin_directory_view(stub_origin_info, stub_origin_visits, stub_origin_snapshot[0], stub_origin_snapshot[1], stub_origin_master_branch, stub_origin_root_directory_sha1, stub_origin_sub_directory_entries, path=stub_origin_sub_directory_path) self.origin_directory_view(stub_origin_info, stub_origin_visits, stub_origin_snapshot[0], stub_origin_snapshot[1], stub_origin_master_branch, stub_origin_root_directory_sha1, stub_origin_sub_directory_entries, visit_id=stub_visit_id, path=stub_origin_sub_directory_path) self.origin_directory_view(stub_origin_info, stub_origin_visits, stub_origin_snapshot[0], stub_origin_snapshot[1], stub_origin_master_branch, stub_origin_root_directory_sha1, stub_origin_sub_directory_entries, timestamp=stub_visit_unix_ts, path=stub_origin_sub_directory_path) self.origin_directory_view(stub_origin_info, stub_origin_visits, stub_origin_snapshot[0], stub_origin_snapshot[1], stub_origin_master_branch, stub_origin_root_directory_sha1, stub_origin_sub_directory_entries, timestamp=stub_visit_iso_date, path=stub_origin_sub_directory_path) + self.origin_directory_view(stub_origin_info_no_type, stub_origin_visits, + stub_origin_snapshot[0], + stub_origin_snapshot[1], + stub_origin_master_branch, + stub_origin_root_directory_sha1, + stub_origin_sub_directory_entries, + path=stub_origin_sub_directory_path) + + self.origin_directory_view(stub_origin_info_no_type, stub_origin_visits, + stub_origin_snapshot[0], + stub_origin_snapshot[1], + stub_origin_master_branch, + stub_origin_root_directory_sha1, + stub_origin_sub_directory_entries, + visit_id=stub_visit_id, + path=stub_origin_sub_directory_path) + + self.origin_directory_view(stub_origin_info_no_type, stub_origin_visits, + stub_origin_snapshot[0], + stub_origin_snapshot[1], + stub_origin_master_branch, + stub_origin_root_directory_sha1, + stub_origin_sub_directory_entries, + timestamp=stub_visit_unix_ts, + path=stub_origin_sub_directory_path) + + self.origin_directory_view(stub_origin_info_no_type, stub_origin_visits, + stub_origin_snapshot[0], + stub_origin_snapshot[1], + stub_origin_master_branch, + stub_origin_root_directory_sha1, + stub_origin_sub_directory_entries, + timestamp=stub_visit_iso_date, + path=stub_origin_sub_directory_path) + @patch('swh.web.browse.views.utils.snapshot_context.request_content') @patch('swh.web.browse.utils.get_origin_visits') @patch('swh.web.browse.utils.get_origin_visit_snapshot') @patch('swh.web.browse.utils.service') @patch('swh.web.browse.views.origin.service') @patch('swh.web.browse.views.utils.snapshot_context.service') + @patch('swh.web.browse.views.origin.get_origin_info') @istest - def origin_request_errors(self, mock_snapshot_service, - mock_origin_service, - mock_utils_service, - mock_get_origin_visit_snapshot, - mock_get_origin_visits, - mock_request_content): - - mock_origin_service.lookup_origin.side_effect = \ + def test_origin_request_errors(self, mock_get_origin_info, + mock_snapshot_service, + mock_origin_service, + mock_utils_service, + mock_get_origin_visit_snapshot, + mock_get_origin_visits, + mock_request_content): + + mock_get_origin_info.side_effect = \ NotFoundExc('origin not found') url = reverse('browse-origin-visits', kwargs={'origin_type': 'foo', 'origin_url': 'bar'}) resp = self.client.get(url) self.assertEquals(resp.status_code, 404) self.assertTemplateUsed('error.html') self.assertContains(resp, 'origin not found', status_code=404) mock_utils_service.lookup_origin.side_effect = None mock_utils_service.lookup_origin.return_value = origin_info_test_data mock_get_origin_visits.return_value = [] url = reverse('browse-origin-directory', kwargs={'origin_type': 'foo', 'origin_url': 'bar'}) resp = self.client.get(url) self.assertEquals(resp.status_code, 404) self.assertTemplateUsed('error.html') self.assertContains(resp, "No SWH visit", status_code=404) mock_get_origin_visits.return_value = stub_origin_visits mock_get_origin_visit_snapshot.side_effect = \ NotFoundExc('visit not found') url = reverse('browse-origin-directory', kwargs={'origin_type': 'foo', 'origin_url': 'bar'}, query_params={'visit_id': len(stub_origin_visits)+1}) resp = self.client.get(url) self.assertEquals(resp.status_code, 404) self.assertTemplateUsed('error.html') self.assertRegex(resp.content.decode('utf-8'), 'Visit.*not found') mock_get_origin_visits.return_value = stub_origin_visits mock_get_origin_visit_snapshot.side_effect = None mock_get_origin_visit_snapshot.return_value = ([], []) url = reverse('browse-origin-directory', kwargs={'origin_type': 'foo', 'origin_url': 'bar'}) resp = self.client.get(url) self.assertEquals(resp.status_code, 404) self.assertTemplateUsed('error.html') self.assertRegex(resp.content.decode('utf-8'), 'Origin.*has an empty list of branches') mock_get_origin_visit_snapshot.return_value = stub_origin_snapshot mock_utils_service.lookup_directory.side_effect = \ NotFoundExc('Directory not found') url = reverse('browse-origin-directory', kwargs={'origin_type': 'foo', 'origin_url': 'bar'}) resp = self.client.get(url) self.assertEquals(resp.status_code, 404) self.assertTemplateUsed('error.html') self.assertContains(resp, 'Directory not found', status_code=404) mock_origin_service.lookup_origin.side_effect = None mock_origin_service.lookup_origin.return_value = origin_info_test_data mock_get_origin_visits.return_value = [] url = reverse('browse-origin-content', kwargs={'origin_type': 'foo', 'origin_url': 'bar', 'path': 'foo'}) resp = self.client.get(url) self.assertEquals(resp.status_code, 404) self.assertTemplateUsed('error.html') self.assertContains(resp, "No SWH visit", status_code=404) mock_get_origin_visits.return_value = stub_origin_visits mock_get_origin_visit_snapshot.side_effect = \ NotFoundExc('visit not found') url = reverse('browse-origin-content', kwargs={'origin_type': 'foo', 'origin_url': 'bar', 'path': 'foo'}, query_params={'visit_id': len(stub_origin_visits)+1}) resp = self.client.get(url) self.assertEquals(resp.status_code, 404) self.assertTemplateUsed('error.html') self.assertRegex(resp.content.decode('utf-8'), 'Visit.*not found') mock_get_origin_visits.return_value = stub_origin_visits mock_get_origin_visit_snapshot.side_effect = None mock_get_origin_visit_snapshot.return_value = ([], []) url = reverse('browse-origin-content', kwargs={'origin_type': 'foo', 'origin_url': 'bar', 'path': 'baz'}) resp = self.client.get(url) self.assertEquals(resp.status_code, 404) self.assertTemplateUsed('error.html') self.assertRegex(resp.content.decode('utf-8'), 'Origin.*has an empty list of branches') mock_get_origin_visit_snapshot.return_value = stub_origin_snapshot mock_snapshot_service.lookup_directory_with_path.return_value = \ {'target': stub_content_text_data['checksums']['sha1']} mock_request_content.side_effect = \ NotFoundExc('Content not found') url = reverse('browse-origin-content', kwargs={'origin_type': 'foo', 'origin_url': 'bar', 'path': 'baz'}) resp = self.client.get(url) self.assertEquals(resp.status_code, 404) self.assertTemplateUsed('error.html') self.assertContains(resp, 'Content not found', status_code=404) - @patch('swh.web.browse.utils.get_origin_visits') - @patch('swh.web.browse.utils.get_origin_visit_snapshot') - @patch('swh.web.browse.utils.service') - @patch('swh.web.browse.views.origin.service') - @istest - def origin_branches(self, mock_origin_service, - mock_utils_service, - mock_get_origin_visit_snapshot, - mock_get_origin_visits): - mock_get_origin_visits.return_value = stub_origin_visits - mock_get_origin_visit_snapshot.return_value = stub_origin_snapshot - mock_utils_service.lookup_origin.return_value = stub_origin_info - - url_args = {'origin_type': stub_origin_info['type'], - 'origin_url': stub_origin_info['url']} + @nottest + def origin_branches_test(self, origin_info, origin_snapshot): + url_args = {'origin_type': origin_info['type'], + 'origin_url': origin_info['url']} url = reverse('browse-origin-branches', kwargs=url_args) resp = self.client.get(url) + self.assertEquals(resp.status_code, 200) self.assertTemplateUsed('branches.html') - origin_branches = stub_origin_snapshot[0] - origin_releases = stub_origin_snapshot[1] + origin_branches = origin_snapshot[0] + origin_releases = origin_snapshot[1] origin_branches_url = \ reverse('browse-origin-branches', kwargs=url_args) self.assertContains(resp, 'Branches (%s)' % (origin_branches_url, len(origin_branches))) origin_releases_url = \ reverse('browse-origin-releases', kwargs=url_args) self.assertContains(resp, 'Releases (%s)' % (origin_releases_url, len(origin_releases))) self.assertContains(resp, '', count=len(origin_branches)) for branch in origin_branches: browse_branch_url = reverse('browse-origin-directory', - kwargs={'origin_type': stub_origin_info['type'], - 'origin_url': stub_origin_info['url']}, + kwargs={'origin_type': origin_info['type'], + 'origin_url': origin_info['url']}, query_params={'branch': branch['name']}) self.assertContains(resp, '%s' % (escape(browse_branch_url), branch['name'])) browse_revision_url = reverse('browse-revision', kwargs={'sha1_git': branch['revision']}, - query_params={'origin_type': stub_origin_info['type'], - 'origin_url': stub_origin_info['url']}) + query_params={'origin_type': origin_info['type'], + 'origin_url': origin_info['url']}) self.assertContains(resp, '%s' % (escape(browse_revision_url), branch['revision'][:7])) @patch('swh.web.browse.utils.get_origin_visits') @patch('swh.web.browse.utils.get_origin_visit_snapshot') @patch('swh.web.browse.utils.service') @patch('swh.web.browse.views.origin.service') @istest - def origin_releases(self, mock_origin_service, + def origin_branches(self, mock_origin_service, mock_utils_service, mock_get_origin_visit_snapshot, mock_get_origin_visits): mock_get_origin_visits.return_value = stub_origin_visits mock_get_origin_visit_snapshot.return_value = stub_origin_snapshot mock_utils_service.lookup_origin.return_value = stub_origin_info - url_args = {'origin_type': stub_origin_info['type'], - 'origin_url': stub_origin_info['url']} + self.origin_branches_test(stub_origin_info, stub_origin_snapshot) + + self.origin_branches_test(stub_origin_info_no_type, stub_origin_snapshot) + + + @nottest + def origin_releases_test(self, origin_info, origin_snapshot): + url_args = {'origin_type': origin_info['type'], + 'origin_url': origin_info['url']} url = reverse('browse-origin-releases', kwargs=url_args) resp = self.client.get(url) self.assertEquals(resp.status_code, 200) self.assertTemplateUsed('releases.html') - origin_branches = stub_origin_snapshot[0] - origin_releases = stub_origin_snapshot[1] + origin_branches = origin_snapshot[0] + origin_releases = origin_snapshot[1] origin_branches_url = \ reverse('browse-origin-branches', kwargs=url_args) self.assertContains(resp, 'Branches (%s)' % (origin_branches_url, len(origin_branches))) origin_releases_url = \ reverse('browse-origin-releases', kwargs=url_args) self.assertContains(resp, 'Releases (%s)' % (origin_releases_url, len(origin_releases))) self.assertContains(resp, '', count=len(origin_releases)) for release in origin_releases: browse_release_url = reverse('browse-release', kwargs={'sha1_git': release['id']}, - query_params={'origin_type': stub_origin_info['type'], - 'origin_url': stub_origin_info['url']}) + query_params={'origin_type': origin_info['type'], + 'origin_url': origin_info['url']}) self.assertContains(resp, '%s' % (escape(browse_release_url), release['name'])) + + @patch('swh.web.browse.utils.get_origin_visits') + @patch('swh.web.browse.utils.get_origin_visit_snapshot') + @patch('swh.web.browse.utils.service') + @patch('swh.web.browse.views.origin.service') + @istest + def origin_releases(self, mock_origin_service, + mock_utils_service, + mock_get_origin_visit_snapshot, + mock_get_origin_visits): + mock_get_origin_visits.return_value = stub_origin_visits + mock_get_origin_visit_snapshot.return_value = stub_origin_snapshot + mock_utils_service.lookup_origin.return_value = stub_origin_info + + self.origin_releases_test(stub_origin_info, stub_origin_snapshot) + self.origin_releases_test(stub_origin_info_no_type, stub_origin_snapshot) +