diff --git a/CHANGES.rst b/CHANGES.rst index ec128116..ab7d76b6 100644 --- a/CHANGES.rst +++ b/CHANGES.rst @@ -1181,7 +1181,7 @@ pywb 0.9.6 changelist pywb 0.9.5 changelist ~~~~~~~~~~~~~~~~~~~~~ -* s3 loading: support ``s3://`` scheme in block loader, allowing for loading index and archive files from s3. ``boto`` library must be installed seperately +* s3 loading: support ``s3://`` scheme in block loader, allowing for loading index and archive files from s3. ``boto`` library must be installed separately via ``pip install boto``. Attempt default boto auth path, and if that fails, attempt anonymous s3 connection. * Wombat/Client-Side Rewrite Customizations: New ``rewrite_opts.client`` settings from ``config.yaml`` are passed directly to wombat as json. @@ -1277,7 +1277,7 @@ pywb 0.9.1 changelist * cdx server query: add support for ``url=*.host`` and ``url=host/*`` as shortcuts for ``matchType=domain`` and ``matchType=prefix`` -* zipnum cdx cluster: support loading index shared from prefix path instead of seperate location file. +* zipnum cdx cluster: support loading index shared from prefix path instead of separate location file. The ``shard_index_loc`` config property may contain match and replace properties. Regex replacement is then used to obtain path prefix from the shard prefix path. @@ -1643,7 +1643,7 @@ pywb 0.4.7 changelist * Rewrite: Parsing of html as raw bytes instead of decode/encode, detection still needed for non-ascii compatible encoding. -* Indexing: Refactoring of cdx-indexer using a seperate 'archive record iterator' and pluggable cdx writer classes. Groundwork for creating custom indexers. +* Indexing: Refactoring of cdx-indexer using a separate 'archive record iterator' and pluggable cdx writer classes. Groundwork for creating custom indexers. * Indexing: Support for 9 field cdx formats with -9 flag. diff --git a/pywb/apps/frontendapp.py b/pywb/apps/frontendapp.py index af25ea68..3129b240 100644 --- a/pywb/apps/frontendapp.py +++ b/pywb/apps/frontendapp.py @@ -599,7 +599,7 @@ class FrontEndApp(object): and message. :param dict environ: The WSGI environment dictionary for the request - :param str err_type: The identifier for type of error that occured + :param str err_type: The identifier for type of error that occurred :param str url: The url of the archived page that was requested """ raise AppPageNotFound(err_type, url) diff --git a/pywb/indexer/cdxindexer.py b/pywb/indexer/cdxindexer.py index 23cb3490..77a8782b 100644 --- a/pywb/indexer/cdxindexer.py +++ b/pywb/indexer/cdxindexer.py @@ -384,7 +384,7 @@ url timestamp { ... } output_help = """ Output file or directory. -- If directory, each input file is written to a seperate output file +- If directory, each input file is written to a separate output file with a .cdx extension - If output is '-', output is written to stdout """ diff --git a/pywb/manager/aclmanager.py b/pywb/manager/aclmanager.py index 3305b912..25fa16f0 100644 --- a/pywb/manager/aclmanager.py +++ b/pywb/manager/aclmanager.py @@ -102,11 +102,11 @@ class ACLManager(CollectionsManager): except IOError as io: if must_exist: - print('Error Occured: ' + str(io)) + print('Error Occurred: ' + str(io)) return False except Exception as e: - print('Error Occured: ' + str(e)) + print('Error Occurred: ' + str(e)) return False def save_acl(self, r=None): diff --git a/pywb/rewrite/html_rewriter.py b/pywb/rewrite/html_rewriter.py index f10d861a..a934cb49 100644 --- a/pywb/rewrite/html_rewriter.py +++ b/pywb/rewrite/html_rewriter.py @@ -268,7 +268,7 @@ class HTMLRewriterMixin(StreamingRewriter): unesc_value = self.try_unescape(value) rewritten_value = self.url_rewriter.rewrite(unesc_value, mod, force_abs) - # if no rewriting has occured, ensure we return original, not reencoded value + # if no rewriting has occurred, ensure we return original, not reencoded value if rewritten_value == value: return orig_value @@ -668,7 +668,7 @@ class HTMLRewriter(HTMLRewriterMixin, HTMLParser): if self.parse_comments: #data = self._rewrite_script(data) - # Rewrite with seperate HTMLRewriter + # Rewrite with separate HTMLRewriter comment_rewriter = HTMLRewriter(self.url_rewriter, defmod=self.defmod) diff --git a/pywb/utils/binsearch.py b/pywb/utils/binsearch.py index add2f423..205c1c58 100644 --- a/pywb/utils/binsearch.py +++ b/pywb/utils/binsearch.py @@ -150,7 +150,7 @@ def iter_exact(reader, key, token=b' '): """ Create an iterator which iterates over lines where the first field matches the 'key', equivalent to token + sep prefix. - Default field termin_ator/seperator is ' ' + Default field termin_ator/separator is ' ' """ return iter_prefix(reader, key + token) diff --git a/pywb/vueui/src/i18n.js b/pywb/vueui/src/i18n.js index 17f18237..a600ed04 100644 --- a/pywb/vueui/src/i18n.js +++ b/pywb/vueui/src/i18n.js @@ -32,7 +32,7 @@ export class PywbI18N { getMonth(id, type='long') { return decodeURIComponent(this.config[PywbI18N.monthIdPrefix[id]+'_'+type]); } - // can get long (default) or short day string or intial + // can get long (default) or short day string or initial // PywbI18N expects to receive day's initials like: // config.mon_short, config.tue_long, ...., config._short, config._long getWeekDay(id, type='long') { diff --git a/tests/test_auto_colls.py b/tests/test_auto_colls.py index cb7ecf69..726bd141 100644 --- a/tests/test_auto_colls.py +++ b/tests/test_auto_colls.py @@ -537,7 +537,7 @@ class TestManagedColls(CollsDirMixin, BaseConfigTest): main(['template', 'foo', '--remove', 'query_html']) def test_err_no_such_coll(self): - """ Test error adding warc to non-existant collection + """ Test error adding warc to non-existent collection """ warc1 = self._get_sample_warc('example.warc.gz') diff --git a/tests/test_integration.py b/tests/test_integration.py index 68c2eb7b..e131ab3c 100644 --- a/tests/test_integration.py +++ b/tests/test_integration.py @@ -400,7 +400,7 @@ class TestWbIntegration(BaseConfigTest): assert resp.status_int == 200 assert resp.headers['Content-Location'].endswith('/pywb/20140126200928{0}/http://www.iana.org/domains/root/db'.format(fmod)) - def test_not_existant_warc_other_capture(self, fmod): + def test_not_existent_warc_other_capture(self, fmod): resp = self.get('/pywb/20140703030321{0}/http://example.com/?example=2', fmod) assert resp.status_int == 200 assert resp.headers['Content-Location'].endswith('/pywb/20140603030341{0}/http://example.com?example=2'.format(fmod)) @@ -410,7 +410,7 @@ class TestWbIntegration(BaseConfigTest): assert resp.status_int == 200 assert resp.headers['Content-Location'].endswith('/pywb/20140603030341{0}/http://example.com?example=2'.format(fmod)) - def test_not_existant_warc_no_other(self, fmod): + def test_not_existent_warc_no_other(self, fmod): resp = self.get('/pywb/20140703030321{0}/http://example.com/?example=3', fmod, status=503) assert resp.status_int == 503