Skip to content

Format Detection API

src.file_parser.format_detector

Format detection for diabetes device data files.

This module provides functionality to detect device formats by examining file structure. It validates only the presence of required tables and columns, without checking data content.

logger = logging.getLogger(__name__) module-attribute

parser = argparse.ArgumentParser(description='Diabetes Data Format Detection Tool') module-attribute

args = parser.parse_args() module-attribute

file_path = Path(args.file_path) module-attribute

registry = FormatRegistry() module-attribute

detector = FormatDetector(registry) module-attribute

ValidationResult

Container for structure validation results.

Source code in src/file_parser/format_detector.py 
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
class ValidationResult:
    """Container for structure validation results."""

    def __init__(self):
        self.missing_tables: List[str] = []
        self.missing_columns: Dict[str, List[str]] = {}  # table: [columns]

    def has_errors(self) -> bool:
        """Check if any validation errors exist."""
        return bool(self.missing_tables or self.missing_columns)

    def __str__(self) -> str:
        """Format validation errors as string."""
        errors = []
        if self.missing_tables:
            errors.append(f"Missing tables: {', '.join(self.missing_tables)}")
        if self.missing_columns:
            for current_table, columns in self.missing_columns.items():
                errors.append(
                    f"Missing required columns in {current_table}: {', '.join(columns)}"
                )
        return "\n".join(errors)

missing_tables: List[str] = [] instance-attribute

missing_columns: Dict[str, List[str]] = {} instance-attribute

__init__()

Source code in src/file_parser/format_detector.py 
32
33
34
def __init__(self):
    self.missing_tables: List[str] = []
    self.missing_columns: Dict[str, List[str]] = {}  # table: [columns]

has_errors() -> bool

Check if any validation errors exist.

Source code in src/file_parser/format_detector.py 
36
37
38
def has_errors(self) -> bool:
    """Check if any validation errors exist."""
    return bool(self.missing_tables or self.missing_columns)

__str__() -> str

Format validation errors as string.

Source code in src/file_parser/format_detector.py 
40
41
42
43
44
45
46
47
48
49
50
def __str__(self) -> str:
    """Format validation errors as string."""
    errors = []
    if self.missing_tables:
        errors.append(f"Missing tables: {', '.join(self.missing_tables)}")
    if self.missing_columns:
        for current_table, columns in self.missing_columns.items():
            errors.append(
                f"Missing required columns in {current_table}: {', '.join(columns)}"
            )
    return "\n".join(errors)

FormatDetector

Detects device formats by examining file structure.

Source code in src/file_parser/format_detector.py 
 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
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
class FormatDetector:
    """Detects device formats by examining file structure."""

    def __init__(self, format_registry: FormatRegistry):
        """initialise detector with format registry."""
        self._registry = format_registry

    def detect_format(
        self, path: Path
    ) -> Tuple[Optional[DeviceFormat], Optional[str], Dict[str, ValidationResult]]:
        """Detect format of provided file.

        Args:
            path: Path to the file to check

        Returns:
            Tuple containing:
                - Matched format (or None)
                - Error message (or None)
                - Dictionary of validation results per format tried

        Example:
            >>> detector = FormatDetector(registry)
            >>> fmt, error, results = detector.detect_format(Path("data.sqlite"))
            >>> if fmt:
            ...     print(f"Matched format: {fmt.name}")
            ... else:
            ...     print(f"No match: {error}")
        """
        logger.debug("Starting format detection for: %s", path)
        val_results = {}

        try:
            # Validate file exists and is readable
            if not self._validate_file_exists(path):
                return None, f"File not found or not accessible: {path}", {}

            # Get potential formats based on file extension
            potential_formats = self._registry.get_formats_for_file(path)
            if not potential_formats:
                return None, f"No formats available for {path.suffix} files", {}

            # Try each format
            for fmt in potential_formats:
                try:
                    val_test_result = ValidationResult()
                    if self._validate_format(path, fmt, val_test_result):
                        logger.debug("Successfully matched format: %s", fmt.name)
                        return fmt, None, val_results
                    val_results[fmt.name] = val_test_result
                except FormatValidationError as e:
                    logger.debug("Error validating format %s: %s", fmt.name, str(e))
                    continue

            return None, "No matching format found", val_results

        except FileAccessError as e:
            logger.error("Unexpected error during format detection: %s", str(e))
            return None, f"Detection error: {str(e)}", {}

    def _validate_file_exists(self, path: Path) -> bool:
        """Validate file exists and is accessible."""
        try:
            return path.exists() and path.is_file()
        except Exception as e:
            raise FileAccessError(f"Error occurred: {str(e)}") from e

    def _validate_format(
        self, path: Path, fmt: DeviceFormat, validation_result: ValidationResult
    ) -> bool:
        """Validate if file matches format definition."""
        for config in fmt.files:
            validator = self._get_validator(config.file_type)
            if validator is None:
                logger.warning("No validator available for %s", config.file_type.value)
                return False
            try:
                if not validator(path, config, validation_result):
                    return False
            except FormatValidationError as e:
                logger.debug("Validation failed: %s", {str(e)})
                return False
        return True

    def _get_validator(self, file_type: FileType):
        """Get appropriate validation function for file type."""
        validators = {
            FileType.SQLITE: self._validate_sqlite,
            FileType.CSV: self._validate_csv,
            FileType.JSON: self._validate_json,
            FileType.XML: self._validate_xml,
        }
        return validators.get(file_type)

    def _validate_sqlite(
        self, path: Path, config, val_result: ValidationResult
    ) -> bool:
        """Validate SQLite file structure."""
        try:
            engine = create_engine(f"sqlite:///{path}")
            inspector = inspect(engine)

            # Get all tables (case sensitive)
            actual_tables = {name: name for name in inspector.get_table_names()}

            # Check each required table
            for required_table in config.tables:
                table_name = required_table.name
                if table_name not in actual_tables:
                    val_result.missing_tables.append(required_table.name)
                    continue

                # Check columns
                columns = inspector.get_columns(table_name)
                column_names = {col["name"] for col in columns}

                # Check required columns exist in file
                required_columns = {
                    col.source_name
                    for col in required_table.columns
                    if col.requirement != ColumnRequirement.OPTIONAL
                }
                missing = required_columns - column_names
                if missing:
                    val_result.missing_columns[required_table.name] = [
                        col.source_name
                        for col in required_table.columns
                        if col.requirement != ColumnRequirement.OPTIONAL
                        and col.source_name in missing
                    ]

            return not val_result.has_errors()

        except FormatValidationError as e:
            logger.debug("SQLite validation error: %s", str(e))
            return False

    def _validate_csv(self, path: Path, config, val_result: ValidationResult) -> bool:
        """Validate CSV file structure."""
        try:
            # CSV should have exactly one table
            csv_table = config.tables[0]

            # If the format specifies a header_row use it directly
            header_row = getattr(csv_table, "header_row", None)
            if header_row is not None:
                header_found = False
                with open(path, encoding="utf-8", newline="") as fh:
                    reader = csv.reader(fh)
                    for idx, row in enumerate(reader):
                        if idx == header_row:
                            # normalize column names: strip whitespace and lowercase
                            row_columns = {
                                str(col).strip().lower()
                                for col in row
                                if col is not None
                            }
                            header_found = True
                            break

                if not header_found:
                    # requested header row does not exist in file
                    val_result.missing_columns[""] = [
                        col.source_name
                        for col in csv_table.columns
                        if col.requirement != ColumnRequirement.OPTIONAL
                    ]
                    return False

                required_columns = {
                    col.source_name.strip().lower()
                    for col in csv_table.columns
                    if col.requirement != ColumnRequirement.OPTIONAL
                }

                missing = required_columns - row_columns
                if missing:
                    val_result.missing_columns[csv_table.name] = [
                        col.source_name
                        for col in csv_table.columns
                        if col.requirement != ColumnRequirement.OPTIONAL
                        and col.source_name.strip().lower() in missing
                    ]
                    return False

                return True

            # No header_row specified: keep scanning first 4 rows for a header
            df = pd.read_csv(path, nrows=4, header=None)

            # Check each of the first 4 rows to see if it contains valid column headers
            found_header_row = None
            for row_idx in range(min(4, len(df))):
                # normalise string values: strip whitespace and lowercase
                row_columns = {str(col).strip().lower() for col in df.iloc[row_idx]}
                logger.debug("CSV header row %d: %s", row_idx, row_columns)

                required_columns = {
                    col.source_name.strip().lower()
                    for col in csv_table.columns
                    if col.requirement != ColumnRequirement.OPTIONAL
                }

                missing = required_columns - row_columns

                # If this row has all required columns, treat it as the header
                if not missing:
                    found_header_row = row_idx
                    break

            if found_header_row is None:
                # No valid header found in first 4 rows
                val_result.missing_columns[""] = [
                    col.source_name
                    for col in csv_table.columns
                    if col.requirement != ColumnRequirement.OPTIONAL
                ]
                return False

            # Successfully found header row
            return True

        except FormatValidationError as e:
            logger.debug("CSV validation error: %s", str(e))
            return False

    def _validate_json(self, path: Path, config, val_result: ValidationResult) -> bool:
        """Validate JSON file structure."""
        try:
            with open(path, encoding="utf-8") as f:
                data = json.load(f)

            for json_table in config.tables:
                if isinstance(data, list):
                    if not data:
                        val_result.missing_tables.append(json_table.name)
                        continue
                    record = data[0]
                else:
                    if json_table.name not in data:
                        val_result.missing_tables.append(json_table.name)
                        continue
                    record = (
                        data[json_table.name][0]
                        if isinstance(data[json_table.name], list)
                        else data[json_table.name]
                    )

                # Check required fields
                fields = {k.lower() for k in record.keys()}
                required_fields = {
                    col.source_name.lower()
                    for col in json_table.columns
                    if col.requirement != ColumnRequirement.OPTIONAL
                }
                missing = required_fields - fields
                if missing:
                    val_result.missing_columns[json_table.name] = [
                        col
                        for col in json_table.columns
                        if col.requirement != ColumnRequirement.OPTIONAL
                        and col.source_name.lower() in missing
                    ]

            return not val_result.has_errors()

        except FormatValidationError as e:
            logger.debug("JSON validation error: %s", str(e))
            return False

    def _validate_xml(self, path: Path, config, val_result: ValidationResult) -> bool:
        """Validate XML file structure."""
        try:
            tree = ET.parse(path)
            root = tree.getroot()

            for xml_table in config.tables:
                elements = root.findall(f".//{xml_table.name}")
                if not elements:
                    val_result.missing_tables.append(xml_table.name)
                    continue

                # Check first element
                element = elements[0]
                fields = set()
                fields.update(element.attrib.keys())
                fields.update(child.tag for child in element)
                fields = {f.lower() for f in fields}

                required_fields = {
                    col.source_name.lower()
                    for col in xml_table.columns
                    if col.requirement != ColumnRequirement.OPTIONAL
                }
                missing = required_fields - fields
                if missing:
                    val_result.missing_columns[xml_table.name] = [
                        col
                        for col in xml_table.columns
                        if col.requirement != ColumnRequirement.OPTIONAL
                        and col.source_name.lower() in missing
                    ]

            return not val_result.has_errors()

        except FormatValidationError as e:
            logger.debug("XML validation error: %s", str(e))
            return False

__init__(format_registry: FormatRegistry)

initialise detector with format registry.

Source code in src/file_parser/format_detector.py 
56
57
58
def __init__(self, format_registry: FormatRegistry):
    """initialise detector with format registry."""
    self._registry = format_registry

detect_format(path: Path) -> Tuple[Optional[DeviceFormat], Optional[str], Dict[str, ValidationResult]]

Detect format of provided file.

Parameters:

Name Type Description Default
path Path

Path to the file to check

 required

Returns:

Type Description
Tuple[Optional[DeviceFormat], Optional[str], Dict[str, ValidationResult]]

Tuple containing: - Matched format (or None) - Error message (or None) - Dictionary of validation results per format tried
Example

detector = FormatDetector(registry) fmt, error, results = detector.detect_format(Path("data.sqlite")) if fmt: ... print(f"Matched format: {fmt.name}") ... else: ... print(f"No match: {error}")

Source code in src/file_parser/format_detector.py 
 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
def detect_format(
    self, path: Path
) -> Tuple[Optional[DeviceFormat], Optional[str], Dict[str, ValidationResult]]:
    """Detect format of provided file.

    Args:
        path: Path to the file to check

    Returns:
        Tuple containing:
            - Matched format (or None)
            - Error message (or None)
            - Dictionary of validation results per format tried

    Example:
        >>> detector = FormatDetector(registry)
        >>> fmt, error, results = detector.detect_format(Path("data.sqlite"))
        >>> if fmt:
        ...     print(f"Matched format: {fmt.name}")
        ... else:
        ...     print(f"No match: {error}")
    """
    logger.debug("Starting format detection for: %s", path)
    val_results = {}

    try:
        # Validate file exists and is readable
        if not self._validate_file_exists(path):
            return None, f"File not found or not accessible: {path}", {}

        # Get potential formats based on file extension
        potential_formats = self._registry.get_formats_for_file(path)
        if not potential_formats:
            return None, f"No formats available for {path.suffix} files", {}

        # Try each format
        for fmt in potential_formats:
            try:
                val_test_result = ValidationResult()
                if self._validate_format(path, fmt, val_test_result):
                    logger.debug("Successfully matched format: %s", fmt.name)
                    return fmt, None, val_results
                val_results[fmt.name] = val_test_result
            except FormatValidationError as e:
                logger.debug("Error validating format %s: %s", fmt.name, str(e))
                continue

        return None, "No matching format found", val_results

    except FileAccessError as e:
        logger.error("Unexpected error during format detection: %s", str(e))
        return None, f"Detection error: {str(e)}", {}