単語検索と墨消し

import glasswall


# Load the Glasswall WordSearch library
word_search = glasswall.WordSearch(r"C:\gwpw\libraries\10.0")

# Redact occurrences of the text "lorem" and "ipsum" within the input file, writing the redacted file to a new path
word_search.redact_file(
    input_file=r"C:\gwpw\input_redact\lorem_ipsum.docx",
    output_file=r"C:\gwpw\output\word_search\redact_f2f\lorem_ipsum.docx",
    content_management_policy=glasswall.content_management.policies.WordSearch(
        config={
            "textSearchConfig": {
                "@libVersion": "core2",
                "textList": [
                    {"name": "textItem", "switches": [
                        {"name": "text", "value": "lorem"},
                        {"name": "textSetting", "@replacementChar": "*", "value": "redact"},
                    ]},
                    {"name": "textItem", "switches": [
                        {"name": "text", "value": "ipsum"},
                        {"name": "textSetting", "@replacementChar": "*", "value": "redact"},
                    ]},
                ]
            }
        }
    )
)

import glasswall


# Load the Glasswall WordSearch library
word_search = glasswall.WordSearch(r"C:\gwpw\libraries\10.0")

# Redact occurrences of the text "lorem" and "ipsum" within the input file, writing the redacted file to a new path
result = word_search.redact_file(
    input_file=r"C:\gwpw\input_redact\lorem_ipsum.docx",
    output_file=None,
    content_management_policy=glasswall.content_management.policies.WordSearch(
        config={
            "textSearchConfig": {
                "@libVersion": "core2",
                "textList": [
                    {"name": "textItem", "switches": [
                        {"name": "text", "value": "lorem"},
                        {"name": "textSetting", "@replacementChar": "*", "value": "redact"},
                    ]},
                    {"name": "textItem", "switches": [
                        {"name": "text", "value": "ipsum"},
                        {"name": "textSetting", "@replacementChar": "*", "value": "redact"},
                    ]},
                ]
            }
        }
    )
)

assert result.output_file[:6] == b'PK\x03\x04\x14\x00'
assert result.output_report[:500] == b'<gw:WordSearchStatistics xmlns:gw="http://glasswall.com/namespace">\n\t<gw:DocumentSummary>\n\t\t<gw:TotalSizeInBytes>14292</gw:TotalSizeInBytes>\n\t\t<gw:FileType>docx</gw:FileType>\n\t\t<gw:TotalItemMatchCount>14</gw:TotalItemMatchCount>\n\t</gw:DocumentSummary>\n\t<gw:WordItem>\n\t\t<gw:Name>ipsum</gw:Name>\n\t\t<gw:ItemMatchCount>8</gw:ItemMatchCount>\n\t\t<gw:Locations>\n\t\t\t<gw:Location>\n\t\t\t\t<gw:Offset>120</gw:Offset>\n\t\t\t\t<gw:Page>0</gw:Page>\n\t\t\t\t<gw:Paragraph>0</gw:Paragraph>\n\t\t\t</gw:Location>\n\t\t\t<gw:Location>\n\t\t\t'

import glasswall


# Load the Glasswall WordSearch library
word_search = glasswall.WordSearch(r"C:\gwpw\libraries\10.0")

# Read file from disk to memory
with open(r"C:\gwpw\input_redact\lorem_ipsum.docx", "rb") as f:
    input_bytes = f.read()

# Redact occurrences of the text "lorem" and "ipsum" within the input file, writing the redacted file to a new path
result = word_search.redact_file(
    input_file=input_bytes,
    output_file=r"C:\gwpw\output\word_search\redact_m2f\lorem_ipsum.docx",
    content_management_policy=glasswall.content_management.policies.WordSearch(
        config={
            "textSearchConfig": {
                "@libVersion": "core2",
                "textList": [
                    {"name": "textItem", "switches": [
                        {"name": "text", "value": "lorem"},
                        {"name": "textSetting", "@replacementChar": "*", "value": "redact"},
                    ]},
                    {"name": "textItem", "switches": [
                        {"name": "text", "value": "ipsum"},
                        {"name": "textSetting", "@replacementChar": "*", "value": "redact"},
                    ]},
                ]
            }
        }
    )
)

assert result.output_file[:6] == b'PK\x03\x04\x14\x00'
assert result.output_report[:500] == b'<gw:WordSearchStatistics xmlns:gw="http://glasswall.com/namespace">\n\t<gw:DocumentSummary>\n\t\t<gw:TotalSizeInBytes>14292</gw:TotalSizeInBytes>\n\t\t<gw:FileType>docx</gw:FileType>\n\t\t<gw:TotalItemMatchCount>14</gw:TotalItemMatchCount>\n\t</gw:DocumentSummary>\n\t<gw:WordItem>\n\t\t<gw:Name>ipsum</gw:Name>\n\t\t<gw:ItemMatchCount>8</gw:ItemMatchCount>\n\t\t<gw:Locations>\n\t\t\t<gw:Location>\n\t\t\t\t<gw:Offset>120</gw:Offset>\n\t\t\t\t<gw:Page>0</gw:Page>\n\t\t\t\t<gw:Paragraph>0</gw:Paragraph>\n\t\t\t</gw:Location>\n\t\t\t<gw:Location>\n\t\t\t'

import glasswall


# Load the Glasswall WordSearch library
word_search = glasswall.WordSearch(r"C:\gwpw\libraries\10.0")

# Redact occurrences of the text "lorem" and "ipsum" within each file in the input_directory, writing the redacted file
# to a new path in the output_directory
results = word_search.redact_directory(
    input_directory=r"C:\gwpw\input_redact",
    output_directory=r"C:\gwpw\output\word_search\redact_directory",
    content_management_policy=glasswall.content_management.policies.WordSearch(
        config={
            "textSearchConfig": {
                "@libVersion": "core2",
                "textList": [
                    {"name": "textItem", "switches": [
                        {"name": "text", "value": "lorem"},
                        {"name": "textSetting", "@replacementChar": "*", "value": "redact"},
                    ]},
                    {"name": "textItem", "switches": [
                        {"name": "text", "value": "ipsum"},
                        {"name": "textSetting", "@replacementChar": "*", "value": "redact"},
                    ]},
                ]
            }
        }
    )
)

assert list(results.keys()) == ['lorem_ipsum.docx', 'lorem_ipsum.pptx']
assert all(result.status == 1 for result in results.values())

import glasswall


# Load the Glasswall WordSearch library
word_search = glasswall.WordSearch(r"C:\gwpw\libraries\10.0")

# Redact occurrences of the text "lorem" and "ipsum" within each file in the input_directory, writing the redacted file
# to a new path in the output_directory
results = word_search.redact_directory(
    input_directory=r"C:\gwpw\input_redact_with_unsupported_file_types",
    output_directory=r"C:\gwpw\output\word_search\redact_directory_unsupported",
    content_management_policy=glasswall.content_management.policies.WordSearch(
        config={
            "textSearchConfig": {
                "@libVersion": "core2",
                "textList": [
                    {"name": "textItem", "switches": [
                        {"name": "text", "value": "lorem"},
                        {"name": "textSetting", "@replacementChar": "*", "value": "redact"},
                    ]},
                    {"name": "textItem", "switches": [
                        {"name": "text", "value": "ipsum"},
                        {"name": "textSetting", "@replacementChar": "*", "value": "redact"},
                    ]},
                ]
            }
        }
    ),
    raise_unsupported=False
)

assert list(results.keys()) == ["lorem_ipsum.docx", "lorem_ipsum.pptx", "python-package.yml"]
assert [result.status for result in results.values()] == [1, 1, 0]

print(results["python-package.yml"].__dict__)
# {'status': 0,
# 'output_file': b'',
# 'output_report': b'<gw:WordSearchStatistics xmlns:gw="http://glasswall.com/namespace">\n\t<gw:IssueItem>\n\t\t<gw:Description>File contents could not be accessed</gw:Description>\n\t</gw:IssueItem>\n\t<gw:DocumentSummary>\n\t\t<gw:TotalSizeInBytes>1460</gw:TotalSizeInBytes>\n\t\t<gw:FileType>Unknown</gw:FileType>\n\t\t<gw:TotalItemMatchCount>0</gw:TotalItemMatchCount>\n\t</gw:DocumentSummary>\n\t<gw:WordItem>\n\t\t<gw:Name>ipsum</gw:Name>\n\t\t<gw:ItemMatchCount>0</gw:ItemMatchCount>\n\t\t<gw:Locations/>\n\t</gw:WordItem>\n\t<gw:WordItem>\n\t\t<gw:Name>lorem</gw:Name>\n\t\t<gw:ItemMatchCount>0</gw:ItemMatchCount>\n\t\t<gw:Locations/>\n\t</gw:WordItem>\n</gw:WordSearchStatistics>\n\n'}

import os

import glasswall


# Load the Glasswall Editor library
editor = glasswall.Editor(r"C:\gwpw\libraries\10.0")

# Load the Glasswall WordSearch library
word_search = glasswall.WordSearch(r"C:\gwpw\libraries\10.0")

input_directory = r"C:\gwpw\input_redact_with_unsupported_file_types"
output_directory = r"C:\gwpw\output\word_search\redact_directory_file_format"

# Iterate relative file paths from input_directory
for relative_file in glasswall.utils.list_file_paths(input_directory, absolute=False):
    # Construct absolute paths
    input_file = os.path.join(input_directory, relative_file)
    output_file = os.path.join(output_directory, relative_file)

    # Get the file type of the file
    file_type = editor.determine_file_type(
        input_file=input_file,
        as_string=True,
        raise_unsupported=False
    )

    # Protect only doc and docx files
    if file_type in ["docx", "pptx"]:
        # Redact occurrences of the text "lorem" and "ipsum" within the input file, writing the redacted file to a new path
        word_search.redact_file(
            input_file=input_file,
            output_file=output_file,
            content_management_policy=glasswall.content_management.policies.WordSearch(
                config={
                    "textSearchConfig": {
                        "@libVersion": "core2",
                        "textList": [
                            {"name": "textItem", "switches": [
                                {"name": "text", "value": "lorem"},
                                {"name": "textSetting", "@replacementChar": "*", "value": "redact"},
                            ]},
                            {"name": "textItem", "switches": [
                                {"name": "text", "value": "ipsum"},
                                {"name": "textSetting", "@replacementChar": "*", "value": "redact"},
                            ]},
                        ]
                    }
                }
            )
        )