Release version 0.10.1

Implement incremental updates

CHANGES.rst

@@ -1,6 +1,47 @@
 Changelog
 =========
 
+0.10.1 (2016-08-20)
+-------------------
+
+- Implement incremental updates. [Robert Bradshaw]
+
+  Guarded with an --incremental flag.
+
+  Stores the time of the last update and only downloads issue and
+  pull request data since this time.  All other data is relatively
+  small (likely fetched with a single request) and so is simply
+  re-populated from scratch as before.
+
+
+0.9.0 (2016-03-29)
+------------------
+
+- Fix cloning private repos with basic auth or token. [Kazuki Suda]
+
+0.8.0 (2016-02-14)
+------------------
+
+- Don't store issues which are actually pull requests. [Enrico Tröger]
+
+  This prevents storing pull requests twice since the Github API returns
+  pull requests also as issues. Those issues will be skipped but only if
+  retrieving pull requests is requested as well.
+  Closes #23.
+
+
+0.7.0 (2016-02-02)
+------------------
+
+- Softly fail if not able to read hooks. [Albert Wang]
+
+- Add note about 2-factor auth. [Albert Wang]
+
+- Make user repository search go through endpoint capable of reading
+  private repositories. [Albert Wang]
+
+- Prompt for password if only username given. [Alex Hall]
+
 0.6.0 (2015-11-10)
 ------------------
 

README.rst

@@ -23,15 +23,14 @@ CLI Usage is as follows::
     Github Backup [-h] [-u USERNAME] [-p PASSWORD] [-t TOKEN]
                      [-o OUTPUT_DIRECTORY] [--starred] [--watched] [--all]
                      [--issues] [--issue-comments] [--issue-events] [--pulls]
-                     [--pull-comments] [--pull-commits] [--repositories]
+                     [--pull-comments] [--pull-commits] [--labels] [--hooks]
-                     [--wikis] [--labels] [--hooks] [--skip-existing]
+                     [--milestones] [--repositories] [--wikis]
-                     [-L [LANGUAGES [LANGUAGES ...]]] [-N NAME_REGEX]
+                     [--skip-existing] [-L [LANGUAGES [LANGUAGES ...]]]
-                     [-H GITHUB_HOST] [-O] [-R REPOSITORY] [-P] [-F]
+                     [-N NAME_REGEX] [-H GITHUB_HOST] [-O] [-R REPOSITORY]
-                     [--prefer-ssh] [-v]
+                     [-P] [-F] [--prefer-ssh] [-v]
                      USER
 
-
+    Backup a github account
-    Backup a github users account
 
     positional arguments:
       USER                  github username
@@ -41,7 +40,8 @@ CLI Usage is as follows::
       -u USERNAME, --username USERNAME
                             username for basic auth
       -p PASSWORD, --password PASSWORD
-                            password for basic auth
+                            password for basic auth. If a username is given but
+                            not a password, the password will be prompted for.
       -t TOKEN, --token TOKEN
                             personal access or OAuth token
       -o OUTPUT_DIRECTORY, --output-directory OUTPUT_DIRECTORY
@@ -55,10 +55,12 @@ CLI Usage is as follows::
       --pulls               include pull requests in backup
       --pull-comments       include pull request review comments in backup
       --pull-commits        include pull request commits in backup
+      --labels              include labels in backup
+      --hooks               include hooks in backup (works only when
+                            authenticated)
+      --milestones          include milestones in backup
       --repositories        include repository clone in backup
       --wikis               include wiki clone in backup
-      --labels              include labels in backup
-      --hooks               include web hooks in backup (works only when authenticated)
       --skip-existing       skip project if a backup directory exists
       -L [LANGUAGES [LANGUAGES ...]], --languages [LANGUAGES [LANGUAGES ...]]
                             only allow these languages
@@ -66,7 +68,7 @@ CLI Usage is as follows::
                             python regex to match names against
       -H GITHUB_HOST, --github-host GITHUB_HOST
                             GitHub Enterprise hostname
-      -O, --organization    whether or not this is a query for an organization
+      -O, --organization    whether or not this is an organization user
       -R REPOSITORY, --repository REPOSITORY
                             name of repository to limit backup to
       -P, --private         include private repositories
@@ -76,3 +78,8 @@ CLI Usage is as follows::
 
 
 The package can be used to backup an *entire* organization or repository, including issues and wikis in the most appropriate format (clones for wikis, json files for issues).
+
+Authentication
+==============
+
+Note: Password-based authentication will fail if you have two-factor authentication enabled.

bin/github-backup

@@ -7,6 +7,7 @@ import base64
 import calendar
 import codecs
 import errno
+import getpass
 import json
 import logging
 import os
@@ -15,6 +16,7 @@ import select
 import subprocess
 import sys
 import time
+import urlparse
 import urllib
 import urllib2
 
@@ -94,6 +96,15 @@ def mkdir_p(*args):
             else:
                 raise
 
+def mask_password(url, secret='*****'):
+    parsed = urlparse.urlparse(url)
+
+    if not parsed.password:
+        return url
+    elif parsed.password == 'x-oauth-basic':
+        return url.replace(parsed.username, secret)
+
+    return url.replace(parsed.password, secret)
 
 def parse_args():
     parser = argparse.ArgumentParser(description='Backup a github account',
@@ -109,7 +120,9 @@ def parse_args():
     parser.add_argument('-p',
                         '--password',
                         dest='password',
-                        help='password for basic auth')
+                        help='password for basic auth. '
+                             'If a username is given but not a password, the '
+                             'password will be prompted for.')
     parser.add_argument('-t',
                         '--token',
                         dest='token',
@@ -119,6 +132,11 @@ def parse_args():
                         default='.',
                         dest='output_directory',
                         help='directory at which to backup the repositories')
+    parser.add_argument('-i',
+                        '--incremental',
+                        action='store_true',
+                        dest='incremental',
+                        help='incremental backup')
     parser.add_argument('--starred',
                         action='store_true',
                         dest='include_starred',
@@ -218,18 +236,25 @@ def parse_args():
     return parser.parse_args()
 
 
-def get_auth(args):
+def get_auth(args, encode=True):
     auth = None
+
     if args.token:
-        auth = base64.b64encode(args.token + ':' + 'x-oauth-basic')
+        auth = args.token + ':' + 'x-oauth-basic'
-    elif args.username and args.password:
+    elif args.username:
-        auth = base64.b64encode(args.username + ':' + args.password)
+        if not args.password:
-    elif args.username and not args.password:
+            args.password = getpass.getpass()
-        log_error('You must specify a password for basic auth')
+        auth = args.username + ':' + args.password
-    elif args.password and not args.username:
+    elif args.password:
         log_error('You must specify a username for basic auth')
 
-    return auth
+    if not auth:
+        return None
+
+    if encode == False:
+        return auth
+
+    return base64.b64encode(auth)
 
 
 def get_github_api_host(args):
@@ -241,7 +266,7 @@ def get_github_api_host(args):
     return host
 
 
-def get_github_ssh_host(args):
+def get_github_host(args):
     if args.github_host:
         host = args.github_host
     else:
@@ -249,6 +274,21 @@ def get_github_ssh_host(args):
 
     return host
 
+def get_github_repo_url(args, repository):
+    if args.prefer_ssh:
+        return repository['ssh_url']
+
+    auth = get_auth(args, False)
+    if auth:
+        repo_url = 'https://{0}@{1}/{2}/{3}.git'.format(
+            auth,
+            get_github_host(args),
+            args.user,
+            repository['name'])
+    else:
+        repo_url = repository['clone_url']
+
+    return repo_url
 
 def retrieve_data(args, template, query_args=None, single_request=False):
     auth = get_auth(args)
@@ -378,9 +418,8 @@ def _request_url_error(template, retry_timeout):
 def retrieve_repositories(args):
     log_info('Retrieving repositories')
     single_request = False
-    template = 'https://{0}/users/{1}/repos'.format(
+    template = 'https://{0}/user/repos'.format(
-        get_github_api_host(args),
+        get_github_api_host(args))
-        args.user)
     if args.organization:
         template = 'https://{0}/orgs/{1}/repos'.format(
             get_github_api_host(args),
@@ -398,6 +437,9 @@ def retrieve_repositories(args):
 
 def filter_repositories(args, repositories):
     log_info('Filtering repositories')
+
+    repositories = [r for r in repositories if r['owner']['login'] == args.user]
+
     name_regex = None
     if args.name_regex:
         name_regex = re.compile(args.name_regex)
@@ -422,15 +464,21 @@ def backup_repositories(args, output_directory, repositories):
     log_info('Backing up repositories')
     repos_template = 'https://{0}/repos'.format(get_github_api_host(args))
 
+    if args.incremental:
+        last_update = max(repository['updated_at'] for repository in repositories)
+        last_update_path = os.path.join(output_directory, 'last_update')
+        if os.path.exists(last_update_path):
+            args.since = open(last_update_path).read().strip()
+        else:
+            args.since = None
+    else:
+        args.since = None
+
     for repository in repositories:
         backup_cwd = os.path.join(output_directory, 'repositories')
         repo_cwd = os.path.join(backup_cwd, repository['name'])
         repo_dir = os.path.join(repo_cwd, 'repository')
-
+        repo_url = get_github_repo_url(args, repository)
-        if args.prefer_ssh:
-            repo_url = repository['ssh_url']
-        else:
-            repo_url = repository['clone_url']
 
         if args.include_repository or args.include_everything:
             fetch_repository(repository['name'],
@@ -460,6 +508,8 @@ def backup_repositories(args, output_directory, repositories):
         if args.include_hooks or args.include_everything:
             backup_hooks(args, repo_cwd, repository, repos_template)
 
+    if args.incremental:
+        open(last_update_path, 'w').write(last_update)
 
 def backup_issues(args, repo_cwd, repository, repos_template):
     has_issues_dir = os.path.isdir('{0}/issues/.git'.format(repo_cwd))
@@ -471,6 +521,8 @@ def backup_issues(args, repo_cwd, repository, repos_template):
     mkdir_p(repo_cwd, issue_cwd)
 
     issues = {}
+    issues_skipped = 0
+    issues_skipped_message = ''
     _issue_template = '{0}/{1}/issues'.format(repos_template,
                                               repository['full_name'])
 
@@ -480,14 +532,24 @@ def backup_issues(args, repo_cwd, repository, repos_template):
             'filter': 'all',
             'state': issue_state
         }
+        if args.since:
+            query_args['since'] = args.since
 
         _issues = retrieve_data(args,
                                 _issue_template,
                                 query_args=query_args)
         for issue in _issues:
+            # skip pull requests which are also returned as issues
+            # if retrieving pull requests is requested as well
+            if 'pull_request' in issue and (args.include_pulls or args.include_everything):
+                issues_skipped += 1
+                continue
+
             issues[issue['number']] = issue
 
-    log_info('Saving {0} issues to disk'.format(len(issues.keys())))
+    if issues_skipped:
+        issues_skipped_message = ' (skipped {0} pull requests)'.format(issues_skipped)
+    log_info('Saving {0} issues to disk{1}'.format(len(issues.keys()), issues_skipped_message))
     comments_template = _issue_template + '/{0}/comments'
     events_template = _issue_template + '/{0}/events'
     for number, issue in issues.iteritems():
@@ -520,14 +582,18 @@ def backup_pulls(args, repo_cwd, repository, repos_template):
     for pull_state in pull_states:
         query_args = {
             'filter': 'all',
-            'state': pull_state
+            'state': pull_state,
+            'sort': 'updated',
+            'direction': 'desc',
         }
 
+        # It'd be nice to be able to apply the args.since filter here...
         _pulls = retrieve_data(args,
                                _pulls_template,
                                query_args=query_args)
         for pull in _pulls:
-            pulls[pull['number']] = pull
+            if not args.since or pull['updated_at'] >= args.since:
+                pulls[pull['number']] = pull
 
     log_info('Saving {0} pull requests to disk'.format(len(pulls.keys())))
     comments_template = _pulls_template + '/{0}/comments'
@@ -594,11 +660,14 @@ def backup_hooks(args, repo_cwd, repository, repos_template):
     output_file = '{0}/hooks.json'.format(hook_cwd)
     template = '{0}/{1}/hooks'.format(repos_template,
                                        repository['full_name'])
-    _backup_data(args,
+    try:
-                 'hooks',
+        _backup_data(args,
-                 template,
+                     'hooks',
-                 output_file,
+                     template,
-                 hook_cwd)
+                     output_file,
+                     hook_cwd)
+    except SystemExit:
+        log_info("Unable to read hooks, skipping")
 
 
 def fetch_repository(name, remote_url, local_dir, skip_existing=False):
@@ -607,12 +676,14 @@ def fetch_repository(name, remote_url, local_dir, skip_existing=False):
     if clone_exists and skip_existing:
         return
 
+    masked_remote_url = mask_password(remote_url)
+
     initalized = subprocess.call('git ls-remote ' + remote_url,
                                  stdout=FNULL,
                                  stderr=FNULL,
                                  shell=True)
     if initalized == 128:
-        log_info("Skipping {0} ({1}) since it's not initalized".format(name, remote_url))
+        log_info("Skipping {0} ({1}) since it's not initalized".format(name, masked_remote_url))
         return
 
     if clone_exists:
@@ -625,7 +696,7 @@ def fetch_repository(name, remote_url, local_dir, skip_existing=False):
         logging_subprocess(git_command, None, cwd=local_dir)
     else:
         log_info('Cloning {0} repository from {1} to {2}'.format(name,
-                                                                 remote_url,
+                                                                 masked_remote_url,
                                                                  local_dir))
         git_command = ['git', 'clone', remote_url, local_dir]
         logging_subprocess(git_command, None)

github_backup/__init__.py

@@ -1 +1 @@
-__version__ = '0.6.0'
+__version__ = '0.10.1'