commit 6adbcc2b60e7d7f84540b8b7e5064c54d3042ed1
parent 6218770a47f53c2a6a23f0ed28c452a2fa8ff67b
Author: Natalie Pendragon <natpen@natpen.net>
Date: Sun, 24 May 2020 23:00:23 -0400
Rename fully_qualified_massaged_url to indexable_url
Diffstat:
2 files changed, 11 insertions(+), 11 deletions(-)
diff --git a/gus/crawl.py b/gus/crawl.py
@@ -151,7 +151,7 @@ def index_binary(resource, response):
index_writer = index_storage.open_index().writer()
try:
index_writer.add_document(
- url=resource.fully_qualified_massaged_url,
+ url=resource.indexable_url,
domain=resource.normalized_host,
content_type=response.content_type,
indexed_at=datetime.utcnow(),
@@ -166,7 +166,7 @@ def index_prompt(resource, response):
index_writer = index_storage.open_index().writer()
try:
index_writer.add_document(
- url=resource.fully_qualified_massaged_url,
+ url=resource.indexable_url,
domain=resource.normalized_host,
content_type="input",
prompt=response.prompt,
@@ -182,7 +182,7 @@ def index_content(resource, response):
index_writer = index_storage.open_index().writer()
try:
index_writer.add_document(
- url=resource.fully_qualified_massaged_url,
+ url=resource.indexable_url,
domain=resource.normalized_host,
content_type=response.content_type,
content=response.content,
diff --git a/gus/lib/gemini.py b/gus/lib/gemini.py
@@ -46,7 +46,7 @@ class GeminiResource():
self._normalized_url = None
self._normalized_host = None
self._fully_qualified_url = None
- self._fully_qualified_massaged_url = None
+ self._indexable_url = None
self.contained_resources = None
def urlsplit_featureful(url, fully_qualified_parent_url=None, parent_hostname=None):
@@ -128,20 +128,20 @@ class GeminiResource():
return self._fully_qualified_url
- def _get_fully_qualified_massaged_url(self):
+ def _get_indexable_url(self):
if not self.is_valid:
return None
- if self._fully_qualified_massaged_url is None:
- fully_qualified_massaged_url = self.fully_qualified_url
+ if self._indexable_url is None:
+ indexable_url = self.fully_qualified_url
if self.urlsplit.port == 1965:
- fully_qualified_massaged_url = self.normalized_url.replace(self.urlsplit.hostname.lower() + ":1965", self.urlsplit.hostname.lower(), 1)
- self._fully_qualified_massaged_url = fully_qualified_massaged_url
- return self._fully_qualified_massaged_url
+ indexable_url = self.normalized_url.replace(self.urlsplit.hostname.lower() + ":1965", self.urlsplit.hostname.lower(), 1)
+ self._indexable_url = indexable_url
+ return self._indexable_url
normalized_url = property(_get_normalized_url)
normalized_host = property(_get_normalized_host)
fully_qualified_url = property(_get_fully_qualified_url)
- fully_qualified_massaged_url = property(_get_fully_qualified_massaged_url)
+ indexable_url = property(_get_indexable_url)
def fetch(self):
# NB: this intentionally does NOT fetch the normalized URL, because that could