def docs():
"""Yield documents for bulk indexing."""
# Index a doc of type 'file' so we can build folder listings.
# At the moment, we send to ES in the same worker that does the
# indexing. We could interpose an external queueing system, but I'm
# willing to potentially sacrifice a little speed here for the easy
# management of self-throttling.
file_info = stat(path)
folder_name, file_name = split(rel_path)
# Hard-code the keys that are hard-coded in the browse()
# controller. Merge with the pluggable ones from needles:
doc = dict( # Some non-array fields:
folder=folder_name,
name=file_name,
size=file_info.st_size,
modified=datetime.fromtimestamp(file_info.st_mtime),
is_folder=False,
# And these, which all get mashed into arrays:
**needles)
links = [{
'order':
order,
'heading':
heading,
'items': [{
'icon': icon,
'title': title,
'href': href
} for icon, title, href in items]
} for order, heading, items in chain.from_iterable(linkses)]
if links:
doc['links'] = links
yield es.index_op(doc, doc_type=FILE)
# Index all the lines.
if index_by_line:
for total, annotations_for_this_line, tags in izip(
needles_by_line, annotations_by_line,
es_lines(
finished_tags(lines, chain.from_iterable(refses),
chain.from_iterable(regionses)))):
# Duplicate the file-wide needles into this line:
total.update(needles)
# We bucket tags into refs and regions for ES because later at
# request time we want to be able to merge them individually
# with those from skimmers.
refs_and_regions = bucket(
tags, lambda index_obj: "regions" if isinstance(
index_obj['payload'], basestring) else "refs")
if 'refs' in refs_and_regions:
total['refs'] = refs_and_regions['refs']
if 'regions' in refs_and_regions:
total['regions'] = refs_and_regions['regions']
if annotations_for_this_line:
total['annotations'] = annotations_for_this_line
yield es.index_op(total)
def docs():
"""Yield documents for bulk indexing.
Big Warning: docs also clears the contents of all elements of
needles_by_line because they will no longer be used.
"""
# Index a doc of type 'file' so we can build folder listings.
# At the moment, we send to ES in the same worker that does the
# indexing. We could interpose an external queueing system, but I'm
# willing to potentially sacrifice a little speed here for the easy
# management of self-throttling.
file_info = stat(path)
folder_name, file_name = split(rel_path)
# Hard-code the keys that are hard-coded in the browse()
# controller. Merge with the pluggable ones from needles:
doc = dict(# Some non-array fields:
folder=folder_name,
name=file_name,
size=file_info.st_size,
modified=datetime.fromtimestamp(file_info.st_mtime),
is_folder=False,
# And these, which all get mashed into arrays:
**needles)
links = dictify_links(chain.from_iterable(linkses))
if links:
doc['links'] = links
yield es.index_op(doc, doc_type=FILE)
# Index all the lines.
if index_by_line:
for total, annotations_for_this_line, tags in izip(
needles_by_line,
annotations_by_line,
es_lines(finished_tags(lines,
chain.from_iterable(refses),
chain.from_iterable(regionses)))):
# Duplicate the file-wide needles into this line:
total.update(needles)
# We bucket tags into refs and regions for ES because later at
# request time we want to be able to merge them individually
# with those from skimmers.
refs_and_regions = bucket(tags, lambda index_obj: "regions" if
isinstance(index_obj['payload'], basestring) else
"refs")
if 'refs' in refs_and_regions:
total['refs'] = refs_and_regions['refs']
if 'regions' in refs_and_regions:
total['regions'] = refs_and_regions['regions']
if annotations_for_this_line:
total['annotations'] = annotations_for_this_line
yield es.index_op(total)
# Because needles_by_line holds a reference, total is not
# garbage collected. Since we won't use it again, we can clear
# the contents, saving substantial memory on long files.
total.clear()
def docs():
"""Yield documents for bulk indexing.
Big Warning: docs also clears the contents of all elements of
needles_by_line because they will no longer be used.
"""
# Index a doc of type 'file' so we can build folder listings.
# At the moment, we send to ES in the same worker that does the
# indexing. We could interpose an external queueing system, but I'm
# willing to potentially sacrifice a little speed here for the easy
# management of self-throttling.
file_info = stat(path)
folder_name, file_name = split(rel_path)
# Hard-code the keys that are hard-coded in the browse()
# controller. Merge with the pluggable ones from needles:
doc = dict(# Some non-array fields:
folder=folder_name,
name=file_name,
size=file_info.st_size,
modified=datetime.fromtimestamp(file_info.st_mtime),
is_folder=False,
# And these, which all get mashed into arrays:
**needles)
links = dictify_links(chain.from_iterable(linkses))
if links:
doc['links'] = links
yield es.index_op(doc, doc_type=FILE)
# Index all the lines.
if index_by_line:
for total, annotations_for_this_line, tags in izip(
needles_by_line,
annotations_by_line,
es_lines(finished_tags(lines,
chain.from_iterable(refses),
chain.from_iterable(regionses)))):
# Duplicate the file-wide needles into this line:
total.update(needles)
# We bucket tags into refs and regions for ES because later at
# request time we want to be able to merge them individually
# with those from skimmers.
refs_and_regions = bucket(tags, lambda index_obj: "regions" if
isinstance(index_obj['payload'], basestring) else
"refs")
if 'refs' in refs_and_regions:
total['refs'] = refs_and_regions['refs']
if 'regions' in refs_and_regions:
total['regions'] = refs_and_regions['regions']
if annotations_for_this_line:
total['annotations'] = annotations_for_this_line
yield es.index_op(total)
# Because needles_by_line holds a reference, total is not
# garbage collected. Since we won't use it again, we can clear
# the contents, saving substantial memory on long files.
total.clear()
def docs():
"""Yield documents for bulk indexing."""
# Index a doc of type 'file' so we can build folder listings.
# At the moment, we send to ES in the same worker that does the
# indexing. We could interpose an external queueing system, but I'm
# willing to potentially sacrifice a little speed here for the easy
# management of self-throttling.
file_info = stat(path)
folder_name, file_name = split(rel_path)
# Hard-code the keys that are hard-coded in the browse()
# controller. Merge with the pluggable ones from needles:
doc = dict(# Some non-array fields:
folder=folder_name,
name=file_name,
size=file_info.st_size,
modified=datetime.fromtimestamp(file_info.st_mtime),
is_folder=False,
# And these, which all get mashed into arrays:
**needles)
links = [{'order': order,
'heading': heading,
'items': [{'icon': icon,
'title': title,
'href': href}
for icon, title, href in items]}
for order, heading, items in
chain.from_iterable(linkses)]
if links:
doc['links'] = links
yield es.index_op(doc, doc_type=FILE)
# Index all the lines. If it's an empty file (no lines), don't bother
# ES. It hates empty dicts.
if is_text and needles_by_line:
for total, annotations_for_this_line, tags in izip(
needles_by_line,
annotations_by_line,
es_lines(finished_tags(lines,
chain.from_iterable(refses),
chain.from_iterable(regionses)))):
# Duplicate the file-wide needles into this line:
total.update(needles)
# We bucket tags into refs and regions for ES because later at
# request time we want to be able to merge them individually
# with those from skimmers.
refs_and_regions = bucket(tags, lambda index_obj: "regions" if
isinstance(index_obj['payload'], basestring) else
"refs")
if 'refs' in refs_and_regions:
total['refs'] = refs_and_regions['refs']
if 'regions' in refs_and_regions:
total['regions'] = refs_and_regions['regions']
if annotations_for_this_line:
total['annotations'] = annotations_for_this_line
yield es.index_op(total)
