Skip to content

Commit

Permalink
[formrecognizer] Update to use f-strings in samples (Azure#30675)
Browse files Browse the repository at this point in the history 
* update to fstrings

* update layout and read async samples

* fix remaining async samples

* add more async samples fixes

* add sync sample updates

* run black

* fix changed header
  • Loading branch information
@catalinaperalta
catalinaperalta authored Jun 8, 2023
1 parent f5c682e commit 63fc24d
Show file tree
Hide file tree
Showing 46 changed files with 1,234 additions and 1,460 deletions.
71 changes: 20 additions & 51 deletions ...azure-ai-formrecognizer/samples/v3.2/async_samples/sample_analyze_business_cards_async.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -55,103 +55,69 @@ async def analyze_business_card_async():
business_cards = await poller.result()

for idx, business_card in enumerate(business_cards.documents):
print("--------Analyzing business card #{}--------".format(idx + 1))
print(f"--------Analyzing business card #{idx + 1}--------")
contact_names = business_card.fields.get("ContactNames")
if contact_names:
for contact_name in contact_names.value:
print(
"Contact First Name: {} has confidence: {}".format(
contact_name.value["FirstName"].value,
contact_name.value[
"FirstName"
].confidence,
)
f"Contact First Name: {contact_name.value['FirstName'].value} "
f"has confidence: {contact_name.value['FirstName'].confidence}"
)
print(
"Contact Last Name: {} has confidence: {}".format(
contact_name.value["LastName"].value,
contact_name.value[
"LastName"
].confidence,
)
f"Contact Last Name: {contact_name.value['LastName'].value} has"
f" confidence: {contact_name.value['LastName'].confidence}"
)
company_names = business_card.fields.get("CompanyNames")
if company_names:
for company_name in company_names.value:
print(
"Company Name: {} has confidence: {}".format(
company_name.value, company_name.confidence
)
f"Company Name: {company_name.value} has confidence: {company_name.confidence}"
)
departments = business_card.fields.get("Departments")
if departments:
for department in departments.value:
print(
"Department: {} has confidence: {}".format(
department.value, department.confidence
)
f"Department: {department.value} has confidence: {department.confidence}"
)
job_titles = business_card.fields.get("JobTitles")
if job_titles:
for job_title in job_titles.value:
print(
"Job Title: {} has confidence: {}".format(
job_title.value, job_title.confidence
)
f"Job Title: {job_title.value} has confidence: {job_title.confidence}"
)
emails = business_card.fields.get("Emails")
if emails:
for email in emails.value:
print(
"Email: {} has confidence: {}".format(email.value, email.confidence)
)
print(f"Email: {email.value} has confidence: {email.confidence}")
websites = business_card.fields.get("Websites")
if websites:
for website in websites.value:
print(
"Website: {} has confidence: {}".format(
website.value, website.confidence
)
)
print(f"Website: {website.value} has confidence: {website.confidence}")
addresses = business_card.fields.get("Addresses")
if addresses:
for address in addresses.value:
print(
"Address: {} has confidence: {}".format(
address.value, address.confidence
)
)
print(f"Address: {address.value} has confidence: {address.confidence}")
mobile_phones = business_card.fields.get("MobilePhones")
if mobile_phones:
for phone in mobile_phones.value:
print(
"Mobile phone number: {} has confidence: {}".format(
phone.content, phone.confidence
)
f"Mobile phone number: {phone.content} has confidence: {phone.confidence}"
)
faxes = business_card.fields.get("Faxes")
if faxes:
for fax in faxes.value:
print(
"Fax number: {} has confidence: {}".format(
fax.content, fax.confidence
)
)
print(f"Fax number: {fax.content} has confidence: {fax.confidence}")
work_phones = business_card.fields.get("WorkPhones")
if work_phones:
for work_phone in work_phones.value:
print(
"Work phone number: {} has confidence: {}".format(
work_phone.content, work_phone.confidence
)
f"Work phone number: {work_phone.content} has confidence: {work_phone.confidence}"
)
other_phones = business_card.fields.get("OtherPhones")
if other_phones:
for other_phone in other_phones.value:
print(
"Other phone number: {} has confidence: {}".format(
other_phone.value, other_phone.confidence
)
f"Other phone number: {other_phone.value} has confidence: {other_phone.confidence}"
)


Expand All @@ -162,11 +128,14 @@ async def main():
if __name__ == "__main__":
import sys
from azure.core.exceptions import HttpResponseError

try:
asyncio.run(main())
except HttpResponseError as error:
print("For more information about troubleshooting errors, see the following guide: "
"https://aka.ms/azsdk/python/formrecognizer/troubleshooting")
print(
"For more information about troubleshooting errors, see the following guide: "
"https://aka.ms/azsdk/python/formrecognizer/troubleshooting"
)
# Examples of how to check an HttpResponseError
# Check by error code:
if error.error is not None:
Expand Down
44 changes: 20 additions & 24 deletions ...ure-ai-formrecognizer/samples/v3.2/async_samples/sample_analyze_custom_documents_async.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -65,43 +65,37 @@ async def analyze_custom_documents_async(custom_model_id):
result = await poller.result()

for idx, document in enumerate(result.documents):
print("--------Analyzing document #{}--------".format(idx + 1))
print("Document has type {}".format(document.doc_type))
print("Document has document type confidence {}".format(document.confidence))
print("Document was analyzed with model with ID {}".format(result.model_id))
print(f"--------Analyzing document #{idx + 1}--------")
print(f"Document has type {document.doc_type}")
print(f"Document has document type confidence {document.confidence}")
print(f"Document was analyzed with model with ID {result.model_id}")
for name, field in document.fields.items():
field_value = field.value if field.value else field.content
print("......found field of type '{}' with value '{}' and with confidence {}".format(field.value_type, field_value, field.confidence))
print(
f"......found field of type '{field.value_type}' with value '{field_value}' and with confidence {field.confidence}"
)

# iterate over tables, lines, and selection marks on each page
for page in result.pages:
print("\nLines found on page {}".format(page.page_number))
print(f"\nLines found on page {page.page_number}")
for line in page.lines:
print("...Line '{}'".format(line.content))
print(f"...Line '{line.content}'")
for word in page.words:
print(
"...Word '{}' has a confidence of {}".format(
word.content, word.confidence
)
)
print(f"...Word '{word.content}' has a confidence of {word.confidence}")
if page.selection_marks:
print("\nSelection marks found on page {}".format(page.page_number))
print(f"\nSelection marks found on page {page.page_number}")
for selection_mark in page.selection_marks:
print(
"...Selection mark is '{}' and has a confidence of {}".format(
selection_mark.state, selection_mark.confidence
)
f"...Selection mark is '{selection_mark.state}' and has a confidence of {selection_mark.confidence}"
)

for i, table in enumerate(result.tables):
print("\nTable {} can be found on page:".format(i + 1))
print(f"\nTable {i + 1} can be found on page:")
for region in table.bounding_regions:
print("...{}".format(region.page_number))
print(f"...{region.page_number}")
for cell in table.cells:
print(
"...Cell[{}][{}] has text '{}'".format(
cell.row_index, cell.column_index, cell.content
)
f"...Cell[{cell.row_index}][{cell.column_index}] has text '{cell.content}'"
)
print("-----------------------------------")
# [END analyze_custom_documents_async]
Expand All @@ -110,7 +104,6 @@ async def analyze_custom_documents_async(custom_model_id):
async def main():
model_id = None
if os.getenv("CONTAINER_SAS_URL") and not os.getenv("CUSTOM_BUILT_MODEL_ID"):

from azure.core.credentials import AzureKeyCredential
from azure.ai.formrecognizer.aio import DocumentModelAdministrationClient
from azure.ai.formrecognizer import ModelBuildMode
Expand Down Expand Up @@ -139,11 +132,14 @@ async def main():
if __name__ == "__main__":
import sys
from azure.core.exceptions import HttpResponseError

try:
asyncio.run(main())
except HttpResponseError as error:
print("For more information about troubleshooting errors, see the following guide: "
"https://aka.ms/azsdk/python/formrecognizer/troubleshooting")
print(
"For more information about troubleshooting errors, see the following guide: "
"https://aka.ms/azsdk/python/formrecognizer/troubleshooting"
)
# Examples of how to check an HttpResponseError
# Check by error code:
if error.error is not None:
Expand Down
89 changes: 39 additions & 50 deletions ...re-ai-formrecognizer/samples/v3.2/async_samples/sample_analyze_general_documents_async.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -24,15 +24,20 @@
import os
import asyncio


def format_bounding_region(bounding_regions):
if not bounding_regions:
return "N/A"
return ", ".join("Page #{}: {}".format(region.page_number, format_polygon(region.polygon)) for region in bounding_regions)
return ", ".join(
f"Page #{region.page_number}: {format_polygon(region.polygon)}"
for region in bounding_regions
)


def format_polygon(polygon):
if not polygon:
return "N/A"
return ", ".join(["[{}, {}]".format(p.x, p.y) for p in polygon])
return ", ".join([f"[{p.x}, {p.y}]" for p in polygon])


async def analyze_general_documents():
Expand Down Expand Up @@ -66,105 +71,89 @@ async def analyze_general_documents():
for style in result.styles:
if style.is_handwritten:
print("Document contains handwritten content: ")
print(",".join([result.content[span.offset:span.offset + span.length] for span in style.spans]))
print(
",".join(
[
result.content[span.offset : span.offset + span.length]
for span in style.spans
]
)
)

print("----Key-value pairs found in document----")
for kv_pair in result.key_value_pairs:
if kv_pair.common_name:
print(f"Common name for key value pair: {kv_pair.common_name}")
if kv_pair.key:
print(
"Key '{}' found within '{}' bounding regions".format(
kv_pair.key.content,
format_bounding_region(kv_pair.key.bounding_regions),
)
)
f"Key '{kv_pair.key.content}' found within "
f"'{format_bounding_region(kv_pair.key.bounding_regions)}' bounding regions"
)
if kv_pair.value:
print(
"Value '{}' found within '{}' bounding regions\n".format(
kv_pair.value.content,
format_bounding_region(kv_pair.value.bounding_regions),
)
)
f"Value '{kv_pair.value.content}' found within "
f"'{format_bounding_region(kv_pair.value.bounding_regions)}' bounding regions\n"
)

for page in result.pages:
print("----Analyzing document from page #{}----".format(page.page_number))
print(f"----Analyzing document from page #{page.page_number}----")
print(
"Page has width: {} and height: {}, measured with unit: {}".format(
page.width, page.height, page.unit
)
f"Page has width: {page.width} and height: {page.height}, measured with unit: {page.unit}"
)

for line_idx, line in enumerate(page.lines):
words = line.get_words()
print(
"...Line # {} has {} words and text '{}' within bounding polygon '{}'".format(
line_idx,
len(words),
line.content,
format_polygon(line.polygon),
)
f"...Line #{line_idx} has {len(words)} words and text '{line.content}' within "
f"bounding polygon '{format_polygon(line.polygon)}'"
)

for word in words:
print(
"......Word '{}' has a confidence of {}".format(
word.content, word.confidence
)
f"......Word '{word.content}' has a confidence of {word.confidence}"
)

for selection_mark in page.selection_marks:
print(
"Selection mark is '{}' within bounding polygon '{}' and has a confidence of {}".format(
selection_mark.state,
format_polygon(selection_mark.polygon),
selection_mark.confidence,
)
f"Selection mark is '{selection_mark.state}' within bounding polygon "
f"'{format_polygon(selection_mark.polygon)}' and has a confidence of "
f"{selection_mark.confidence}"
)

for table_idx, table in enumerate(result.tables):
print(
"Table # {} has {} rows and {} columns".format(
table_idx, table.row_count, table.column_count
)
f"Table # {table_idx} has {table.row_count} rows and {table.column_count} columns"
)
for region in table.bounding_regions:
print(
"Table # {} location on page: {} is {}".format(
table_idx,
region.page_number,
format_polygon(region.polygon),
)
f"Table # {table_idx} location on page: {region.page_number} is {format_polygon(region.polygon)}"
)
for cell in table.cells:
print(
"...Cell[{}][{}] has text '{}'".format(
cell.row_index,
cell.column_index,
cell.content,
)
f"...Cell[{cell.row_index}][{cell.column_index}] has text '{cell.content}'"
)
for region in cell.bounding_regions:
print(
"...content on page {} is within bounding polygon '{}'\n".format(
region.page_number,
format_polygon(region.polygon),
)
f"...content on page {region.page_number} is within bounding polygon '{format_polygon(region.polygon)}'\n"
)
print("----------------------------------------")


async def main():
await analyze_general_documents()


if __name__ == "__main__":
import sys
from azure.core.exceptions import HttpResponseError

try:
asyncio.run(main())
except HttpResponseError as error:
print("For more information about troubleshooting errors, see the following guide: "
"https://aka.ms/azsdk/python/formrecognizer/troubleshooting")
print(
"For more information about troubleshooting errors, see the following guide: "
"https://aka.ms/azsdk/python/formrecognizer/troubleshooting"
)
# Examples of how to check an HttpResponseError
# Check by error code:
if error.error is not None:
Expand Down
Loading

0 comments on commit 63fc24d

Please sign in to comment.