Skip to content

Fixes encoding and adds test for encoded characters. #961

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
May 24, 2017
Merged

Fixes encoding and adds test for encoded characters. #961

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
19 changes: 14 additions & 5 deletions language/cloud-client/v1beta2/snippets.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,6 +22,7 @@
"""

import argparse
import sys

from google.cloud import language
from google.cloud.gapic.language.v1beta2 import enums
Expand Down Expand Up @@ -53,7 +54,7 @@ def sentiment_file(gcs_uri):
language_client = language.Client(api_version='v1beta2')

# Instantiates a plain text document.
document = language_client.document_from_url(gcs_uri)
document = language_client.document_from_gcs_url(gcs_uri)

# Detects sentiment in the document. You can also analyze HTML with:
# document.doc_type == language.Document.HTML
Expand Down Expand Up @@ -92,7 +93,7 @@ def entities_file(gcs_uri):
language_client = language.Client(api_version='v1beta2')

# Instantiates a plain text document.
document = language_client.document_from_url(gcs_uri)
document = language_client.document_from_gcs_url(gcs_uri)

# Detects sentiment in the document. You can also analyze HTML with:
# document.doc_type == language.Document.HTML
Expand Down Expand Up @@ -131,7 +132,7 @@ def syntax_file(gcs_uri):
language_client = language.Client(api_version='v1beta2')

# Instantiates a plain text document.
document = language_client.document_from_url(gcs_uri)
document = language_client.document_from_gcs_url(gcs_uri)

# Detects syntax in the document. You can also analyze HTML with:
# document.doc_type == language.Document.HTML
Expand All @@ -152,8 +153,12 @@ def entity_sentiment_text(text):
document.content = text.encode('utf-8')
document.type = enums.Document.Type.PLAIN_TEXT

encoding = enums.EncodingType.UTF32
if sys.maxunicode == 65535:
encoding = enums.EncodingType.UTF16

result = language_client.analyze_entity_sentiment(
document, enums.EncodingType.UTF8)
document, encoding)

for entity in result.entities:
print('Mentions: ')
Expand All @@ -176,8 +181,12 @@ def entity_sentiment_file(gcs_uri):
document.gcs_content_uri = gcs_uri
document.type = enums.Document.Type.PLAIN_TEXT

encoding = enums.EncodingType.UTF32
if sys.maxunicode == 65535:
encoding = enums.EncodingType.UTF16

result = language_client.analyze_entity_sentiment(
document, enums.EncodingType.UTF8)
document, encoding)

for entity in result.entities:
print(u'Name: "{}"'.format(entity.name))
Expand Down
7 changes: 7 additions & 0 deletions language/cloud-client/v1beta2/snippets_test.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -79,3 +79,10 @@ def test_sentiment_entities_file(capsys):
snippets.entity_sentiment_file(TEST_FILE_URL)
out, _ = capsys.readouterr()
assert 'Content : White House' in out


def test_sentiment_entities_utf(capsys):
snippets.entity_sentiment_text(
'foo→bar')
out, _ = capsys.readouterr()
assert 'Begin Offset : 4' in out