Skip to content

Office Word Handler API

auris_tools.officeWordHandler

OfficeWordHandler

Handler for DOCX operations including text extraction and manipulation.

This class provides methods to interact with Microsoft Word documents (DOCX) stored in S3, including reading, extracting text, and text replacement operations.

Source code in auris_tools/officeWordHandler.py 
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
class OfficeWordHandler:
    """
    Handler for DOCX operations including text extraction and manipulation.

    This class provides methods to interact with Microsoft Word documents (DOCX)
    stored in S3, including reading, extracting text, and text replacement operations.
    """

    def __init__(self, config=None):
        """
        Initialize the Office Word handler with AWS configuration.

        Args:
            config: An AWSConfiguration object, or None to use environment variables
        """
        if config is None:
            config = AWSConfiguration()

        # Create a boto3 session with the configuration
        session = boto3.session.Session(**config.get_boto3_session_args())

        # Create an S3 client with additional configuration if needed
        self.s3_client = session.client('s3', **config.get_client_args())
        logging.info(f'Initialized S3 client in region {config.region}')

    def read_from_s3(self, bucket_name, object_name, as_bytes_io=False):
        """
        Read a DOCX file from S3 and return its bytes.

        Args:
            bucket_name: Name of the S3 bucket containing the document
            object_name: Object key of the document in the S3 bucket
            as_bytes_io: If True, return a BytesIO object instead of raw bytes

        Returns:
            bytes or BytesIO: The document content

        Raises:
            Exception: If there is an error retrieving the document
        """
        try:
            response = self.s3_client.get_object(
                Bucket=bucket_name, Key=object_name
            )
            content = response['Body'].read()

            if as_bytes_io:
                return io.BytesIO(content)
            return content
        except Exception as e:
            logging.error(
                f'Error reading document from {bucket_name}/{object_name}: {str(e)}'
            )
            raise Exception(f'Error reading file from S3: {str(e)}')

    def upload_docx(self, docx_document, bucket_name, object_name):
        """
        Upload a DOCX document to S3.

        Args:
            docx_document: The Document object to upload
            bucket_name: Name of the S3 bucket
            object_name: Object key for the document in S3

        Returns:
            bool: True if upload was successful, False otherwise

        Raises:
            Exception: If there is an error uploading the document
        """
        try:
            logging.info(f'Starting upload to S3: {bucket_name}/{object_name}')

            # Convert document to bytes
            temp_stream = io.BytesIO()
            docx_document.save(temp_stream)
            temp_stream.seek(0)
            document_size = len(temp_stream.getvalue())

            # Upload to S3
            self.s3_client.upload_fileobj(
                temp_stream,
                Bucket=bucket_name,
                Key=object_name,
                ExtraArgs={
                    'ContentType': 'application/vnd.openxmlformats-officedocument.wordprocessingml.document'
                },
            )

            logging.info(
                f'Upload finished successfully. Size: {document_size} bytes'
            )
            return True
        except Exception as e:
            logging.error(f'Failed to upload to S3: {str(e)}')
            raise Exception(f'Error uploading file to S3: {str(e)}')

    def get_text_from_bytes(self, bytes_data):
        """
        Extract text from a DOCX file bytes.

        Args:
            bytes_data: The document bytes

        Returns:
            str: Extracted text from the document

        Raises:
            ValueError: If there is an error extracting the text
        """
        try:
            doc = Document(io.BytesIO(bytes_data))
            full_text = []

            # Extract text from paragraphs
            for para in doc.paragraphs:
                full_text.append(para.text)

            # Extract text from tables
            for table in doc.tables:
                for row in table.rows:
                    for cell in row.cells:
                        full_text.append(cell.text)

            return '\n'.join(full_text)
        except Exception as e:
            logging.error(f'Error extracting text from DOCX: {str(e)}')
            raise ValueError(f'Error extracting text from DOCX: {str(e)}')

    def clean_text(self, text):
        """
        Clean extracted text from a DOCX file.

        Args:
            text: Text to clean

        Returns:
            str: Cleaned text
        """
        if not text:
            return ''

        # Basic cleaning (can be extended)
        cleaned_text = text.strip()
        return cleaned_text

    def collect_all_paragraphs(self, document: Document) -> List[Paragraph]:
        """
        Collect all paragraphs from a Document object.

        This method collects paragraphs from the main document body,
        tables, headers, and footers.

        Args:
            document: The Document object

        Returns:
            List[Paragraph]: List of all paragraphs in the document
        """
        paragraphs = list(document.paragraphs)

        for table in document.tables:
            for row in table.rows:
                for cell in row.cells:
                    paragraphs.extend(cell.paragraphs)

        for section in document.sections:
            paragraphs.extend(section.header.paragraphs)
            paragraphs.extend(section.footer.paragraphs)

        return paragraphs

    def replace_placeholder_by_text(
        self,
        paragraphs: List[Paragraph],
        document: Document,
        placeholder: str,
        replacement: str,
        max_count: Optional[int] = None,
    ) -> int:
        """
        Replace placeholder text with replacement in document's XML w:t nodes.

        Args:
            paragraphs: List of paragraphs to process
            document: Document object
            placeholder: Text to find and replace
            replacement: Text to insert instead of placeholder
            max_count: Maximum number of replacements, or None for unlimited

        Returns:
            int: Number of replacements made

        Note:
            This method works at the XML level to ensure proper formatting is preserved.
        """
        count = 0
        WORD_NAMESPACE = (
            'http://schemas.openxmlformats.org/wordprocessingml/2006/main'
        )
        T_TAG = f'{{{WORD_NAMESPACE}}}t'

        if placeholder in replacement:
            logging.warning(
                f'Replacement skipped to avoid recursion: {placeholder} -> {replacement}'
            )
            return 0

        def replace_in_element(element):
            nonlocal count
            for node in element.iter(tag=T_TAG):
                if node.text and placeholder in node.text:
                    remaining = (
                        None if max_count is None else max_count - count
                    )
                    new_text, n = re.subn(
                        re.escape(placeholder),
                        replacement,
                        node.text,
                        count=remaining if remaining else 0,
                    )
                    if n > 0:
                        node.text = new_text
                        count += n
                        if max_count is not None and count >= max_count:
                            return True
            return False

        # Main paragraphs
        for para in paragraphs:
            if replace_in_element(para._element):
                return count

        # Headers/footers
        for section in document.sections:
            for container in [section.header, section.footer]:
                for para in container.paragraphs:
                    if replace_in_element(para._element):
                        return count

        # Tables
        for table in document.tables:
            for row in table.rows:
                for cell in row.cells:
                    for para in cell.paragraphs:
                        if replace_in_element(para._element):
                            return count

        # Hyperlinks
        for rel in document.part.rels.values():
            if rel.reltype == RT.HYPERLINK and placeholder in rel.target_ref:
                logging.info(
                    f'Replacing hyperlink: {rel.target_ref} -> {rel.target_ref.replace(placeholder, replacement)}'
                )
                rel._target = rel.target_ref.replace(placeholder, replacement)
                count += 1

        return count
__init__ 
__init__(config = None)

Initialize the Office Word handler with AWS configuration.

Parameters:

Name Type Description Default
config

An AWSConfiguration object, or None to use environment variables

 None
Source code in auris_tools/officeWordHandler.py 
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
def __init__(self, config=None):
    """
    Initialize the Office Word handler with AWS configuration.

    Args:
        config: An AWSConfiguration object, or None to use environment variables
    """
    if config is None:
        config = AWSConfiguration()

    # Create a boto3 session with the configuration
    session = boto3.session.Session(**config.get_boto3_session_args())

    # Create an S3 client with additional configuration if needed
    self.s3_client = session.client('s3', **config.get_client_args())
    logging.info(f'Initialized S3 client in region {config.region}')
clean_text 
clean_text(text)

Clean extracted text from a DOCX file.

Parameters:

Name Type Description Default
text

Text to clean

 required

Returns:

Name Type Description
str

Cleaned text
Source code in auris_tools/officeWordHandler.py 
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
def clean_text(self, text):
    """
    Clean extracted text from a DOCX file.

    Args:
        text: Text to clean

    Returns:
        str: Cleaned text
    """
    if not text:
        return ''

    # Basic cleaning (can be extended)
    cleaned_text = text.strip()
    return cleaned_text
collect_all_paragraphs 
collect_all_paragraphs(document: Document) -> List[Paragraph]

Collect all paragraphs from a Document object.

This method collects paragraphs from the main document body, tables, headers, and footers.

Parameters:

Name Type Description Default
document Document

The Document object

 required

Returns:

Type Description
List[Paragraph]

List[Paragraph]: List of all paragraphs in the document
Source code in auris_tools/officeWordHandler.py 
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
def collect_all_paragraphs(self, document: Document) -> List[Paragraph]:
    """
    Collect all paragraphs from a Document object.

    This method collects paragraphs from the main document body,
    tables, headers, and footers.

    Args:
        document: The Document object

    Returns:
        List[Paragraph]: List of all paragraphs in the document
    """
    paragraphs = list(document.paragraphs)

    for table in document.tables:
        for row in table.rows:
            for cell in row.cells:
                paragraphs.extend(cell.paragraphs)

    for section in document.sections:
        paragraphs.extend(section.header.paragraphs)
        paragraphs.extend(section.footer.paragraphs)

    return paragraphs
get_text_from_bytes 
get_text_from_bytes(bytes_data)

Extract text from a DOCX file bytes.

Parameters:

Name Type Description Default
bytes_data

The document bytes

 required

Returns:

Name Type Description
str

Extracted text from the document

Raises:

Type Description
ValueError

If there is an error extracting the text
Source code in auris_tools/officeWordHandler.py 
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
def get_text_from_bytes(self, bytes_data):
    """
    Extract text from a DOCX file bytes.

    Args:
        bytes_data: The document bytes

    Returns:
        str: Extracted text from the document

    Raises:
        ValueError: If there is an error extracting the text
    """
    try:
        doc = Document(io.BytesIO(bytes_data))
        full_text = []

        # Extract text from paragraphs
        for para in doc.paragraphs:
            full_text.append(para.text)

        # Extract text from tables
        for table in doc.tables:
            for row in table.rows:
                for cell in row.cells:
                    full_text.append(cell.text)

        return '\n'.join(full_text)
    except Exception as e:
        logging.error(f'Error extracting text from DOCX: {str(e)}')
        raise ValueError(f'Error extracting text from DOCX: {str(e)}')
read_from_s3 
read_from_s3(bucket_name, object_name, as_bytes_io = False)

Read a DOCX file from S3 and return its bytes.

Parameters:

Name Type Description Default
bucket_name

Name of the S3 bucket containing the document

 required
object_name

Object key of the document in the S3 bucket

 required
as_bytes_io

If True, return a BytesIO object instead of raw bytes

 False

Returns:

Type Description

bytes or BytesIO: The document content

Raises:

Type Description
Exception

If there is an error retrieving the document
Source code in auris_tools/officeWordHandler.py 
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
def read_from_s3(self, bucket_name, object_name, as_bytes_io=False):
    """
    Read a DOCX file from S3 and return its bytes.

    Args:
        bucket_name: Name of the S3 bucket containing the document
        object_name: Object key of the document in the S3 bucket
        as_bytes_io: If True, return a BytesIO object instead of raw bytes

    Returns:
        bytes or BytesIO: The document content

    Raises:
        Exception: If there is an error retrieving the document
    """
    try:
        response = self.s3_client.get_object(
            Bucket=bucket_name, Key=object_name
        )
        content = response['Body'].read()

        if as_bytes_io:
            return io.BytesIO(content)
        return content
    except Exception as e:
        logging.error(
            f'Error reading document from {bucket_name}/{object_name}: {str(e)}'
        )
        raise Exception(f'Error reading file from S3: {str(e)}')
replace_placeholder_by_text 
replace_placeholder_by_text(paragraphs: List[Paragraph], document: Document, placeholder: str, replacement: str, max_count: Optional[int] = None) -> int

Replace placeholder text with replacement in document's XML w:t nodes.

Parameters:

Name Type Description Default
paragraphs List[Paragraph]

List of paragraphs to process

 required
document Document

Document object

 required
placeholder str

Text to find and replace

 required
replacement str

Text to insert instead of placeholder

 required
max_count Optional[int]

Maximum number of replacements, or None for unlimited

 None

Returns:

Name Type Description
int int

Number of replacements made
Note

This method works at the XML level to ensure proper formatting is preserved.

Source code in auris_tools/officeWordHandler.py 
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
def replace_placeholder_by_text(
    self,
    paragraphs: List[Paragraph],
    document: Document,
    placeholder: str,
    replacement: str,
    max_count: Optional[int] = None,
) -> int:
    """
    Replace placeholder text with replacement in document's XML w:t nodes.

    Args:
        paragraphs: List of paragraphs to process
        document: Document object
        placeholder: Text to find and replace
        replacement: Text to insert instead of placeholder
        max_count: Maximum number of replacements, or None for unlimited

    Returns:
        int: Number of replacements made

    Note:
        This method works at the XML level to ensure proper formatting is preserved.
    """
    count = 0
    WORD_NAMESPACE = (
        'http://schemas.openxmlformats.org/wordprocessingml/2006/main'
    )
    T_TAG = f'{{{WORD_NAMESPACE}}}t'

    if placeholder in replacement:
        logging.warning(
            f'Replacement skipped to avoid recursion: {placeholder} -> {replacement}'
        )
        return 0

    def replace_in_element(element):
        nonlocal count
        for node in element.iter(tag=T_TAG):
            if node.text and placeholder in node.text:
                remaining = (
                    None if max_count is None else max_count - count
                )
                new_text, n = re.subn(
                    re.escape(placeholder),
                    replacement,
                    node.text,
                    count=remaining if remaining else 0,
                )
                if n > 0:
                    node.text = new_text
                    count += n
                    if max_count is not None and count >= max_count:
                        return True
        return False

    # Main paragraphs
    for para in paragraphs:
        if replace_in_element(para._element):
            return count

    # Headers/footers
    for section in document.sections:
        for container in [section.header, section.footer]:
            for para in container.paragraphs:
                if replace_in_element(para._element):
                    return count

    # Tables
    for table in document.tables:
        for row in table.rows:
            for cell in row.cells:
                for para in cell.paragraphs:
                    if replace_in_element(para._element):
                        return count

    # Hyperlinks
    for rel in document.part.rels.values():
        if rel.reltype == RT.HYPERLINK and placeholder in rel.target_ref:
            logging.info(
                f'Replacing hyperlink: {rel.target_ref} -> {rel.target_ref.replace(placeholder, replacement)}'
            )
            rel._target = rel.target_ref.replace(placeholder, replacement)
            count += 1

    return count
upload_docx 
upload_docx(docx_document, bucket_name, object_name)

Upload a DOCX document to S3.

Parameters:

Name Type Description Default
docx_document

The Document object to upload

 required
bucket_name

Name of the S3 bucket

 required
object_name

Object key for the document in S3

 required

Returns:

Name Type Description
bool

True if upload was successful, False otherwise

Raises:

Type Description
Exception

If there is an error uploading the document
Source code in auris_tools/officeWordHandler.py 
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
def upload_docx(self, docx_document, bucket_name, object_name):
    """
    Upload a DOCX document to S3.

    Args:
        docx_document: The Document object to upload
        bucket_name: Name of the S3 bucket
        object_name: Object key for the document in S3

    Returns:
        bool: True if upload was successful, False otherwise

    Raises:
        Exception: If there is an error uploading the document
    """
    try:
        logging.info(f'Starting upload to S3: {bucket_name}/{object_name}')

        # Convert document to bytes
        temp_stream = io.BytesIO()
        docx_document.save(temp_stream)
        temp_stream.seek(0)
        document_size = len(temp_stream.getvalue())

        # Upload to S3
        self.s3_client.upload_fileobj(
            temp_stream,
            Bucket=bucket_name,
            Key=object_name,
            ExtraArgs={
                'ContentType': 'application/vnd.openxmlformats-officedocument.wordprocessingml.document'
            },
        )

        logging.info(
            f'Upload finished successfully. Size: {document_size} bytes'
        )
        return True
    except Exception as e:
        logging.error(f'Failed to upload to S3: {str(e)}')
        raise Exception(f'Error uploading file to S3: {str(e)}')