20158146015

Committed 12 Dec 2025 06:14AM UTC coverage: 90.787% (+0.3%) from 90.479%

Build # 20158146015

Build Type

push

github

Committed by

bramp

Commit Message

Ignore profile output.

Coverage Stats

12594 of 13872 relevant lines covered (90.79%)

0.91 hits per line

Source File
Press 'n' to go to next uncovered line, 'b' for previous

99.11

/src/build_a_long/pdf_extract/classifier/classifier.py

"""
Rule-based classifier for labeling page elements.

Pipeline order and dependencies
--------------------------------
The classification pipeline operates in two main phases:

1. **Bottom-up Scoring**: All classifiers run independently to identify potential
   candidates (e.g. page numbers, part counts, step numbers) and score them based
   on heuristics. No construction of final elements happens here.

2. **Top-down Construction**: The root `PageClassifier` is invoked to construct
   the final `Page` object. It recursively requests the construction of its
   dependencies (e.g. "Give me the best PageNumber"), which in turn construct
   their own dependencies. This ensures a consistent and validated object tree.

"""

from __future__ import annotations

import logging

from build_a_long.pdf_extract.classifier.bags import (
    BagNumberClassifier,
    LoosePartSymbolClassifier,
    OpenBagClassifier,
)
from build_a_long.pdf_extract.classifier.batch_classification_result import (
    BatchClassificationResult,
)
from build_a_long.pdf_extract.classifier.block_filter import (
    filter_duplicate_blocks,
    filter_overlapping_text_blocks,
)
from build_a_long.pdf_extract.classifier.classification_result import (
    ClassificationResult,
)
from build_a_long.pdf_extract.classifier.classifier_config import ClassifierConfig
from build_a_long.pdf_extract.classifier.pages import (
    PageHintCollection,
)
from build_a_long.pdf_extract.classifier.pages.background_classifier import (
    BackgroundClassifier,
)
from build_a_long.pdf_extract.classifier.pages.divider_classifier import (
    DividerClassifier,
)
from build_a_long.pdf_extract.classifier.pages.page_classifier import PageClassifier
from build_a_long.pdf_extract.classifier.pages.page_number_classifier import (
    PageNumberClassifier,
)
from build_a_long.pdf_extract.classifier.pages.preview_classifier import (
    PreviewClassifier,
)
from build_a_long.pdf_extract.classifier.pages.progress_bar_classifier import (
    ProgressBarClassifier,
)
from build_a_long.pdf_extract.classifier.pages.progress_bar_indicator_classifier import (
    ProgressBarIndicatorClassifier,
)
from build_a_long.pdf_extract.classifier.pages.trivia_text_classifier import (
    TriviaTextClassifier,
)
from build_a_long.pdf_extract.classifier.parts import (
    PartCountClassifier,
    PartNumberClassifier,
    PartsClassifier,
    PartsImageClassifier,
    PartsListClassifier,
    PieceLengthClassifier,
    ScaleClassifier,
    ShineClassifier,
)
from build_a_long.pdf_extract.classifier.removal_reason import RemovalReason
from build_a_long.pdf_extract.classifier.steps import (
    ArrowClassifier,
    DiagramClassifier,
    RotationSymbolClassifier,
    StepClassifier,
    StepCountClassifier,
    StepNumberClassifier,
    SubAssemblyClassifier,
)
from build_a_long.pdf_extract.classifier.text import FontSizeHints, TextHistogram
from build_a_long.pdf_extract.classifier.topological_sort import topological_sort
from build_a_long.pdf_extract.extractor import PageData
from build_a_long.pdf_extract.extractor.bbox import filter_contained
from build_a_long.pdf_extract.extractor.lego_page_elements import (
    PageNumber,
    PartCount,
    PartsList,
    StepNumber,
)
from build_a_long.pdf_extract.extractor.page_blocks import Blocks

logger = logging.getLogger(__name__)

# Pages with more blocks than this threshold will be skipped during classification.
# This avoids O(n²) algorithms (like duplicate detection) that become prohibitively
# slow on pages with thousands of vector drawings. Such pages are typically info
# pages where each character is a separate vector graphic.
# TODO: Add spatial indexing to handle high-block pages efficiently.
MAX_BLOCKS_PER_PAGE = 1000


# TODO require config, so we don't accidentally use default empty config
def classify_elements(
    page: PageData, config: ClassifierConfig | None = None
) -> ClassificationResult:
    """Classify and label elements on a single page using rule-based heuristics.

    Args:
        page: A single PageData object to classify.
        config: Optional classifier configuration with font/page hints.
            If None, uses default empty configuration (no hints).
            For better classification accuracy, pass a config with
            FontSizeHints computed from multiple pages of the same PDF.

    Returns:
        A ClassificationResult object containing the classification results.
    """
    if config is None:
        config = ClassifierConfig()
    classifier = Classifier(config)

    return classifier.classify(page)


def classify_pages(
    pages: list[PageData], pages_for_hints: list[PageData] | None = None
) -> BatchClassificationResult:
    """Classify and label elements across multiple pages using rule-based heuristics.

    This function performs a three-phase process:
    1. Filtering phase: Mark duplicate/similar blocks as removed on each page
    2. Analysis phase: Build font size hints from text properties (excluding
       removed blocks)
    3. Classification phase: Use hints to guide element classification

    Args:
        pages: A list of PageData objects to classify.
        pages_for_hints: Optional list of pages to use for generating font/page hints.
            If None, uses `pages`. This allows generating hints from all pages
            while only classifying a subset (e.g., when using --pages filter).

    Returns:
        BatchClassificationResult containing per-page results and global histogram
    """

    # TODO There is a bunch of duplication in here between hints and non-hints. Refactor

    # Use all pages for hint generation if provided, otherwise use selected pages
    hint_pages = pages_for_hints if pages_for_hints is not None else pages

    # Phase 1: Filter duplicate blocks on each page and track removals
    # Skip pages with too many blocks to avoid O(n²) performance issues
    removed_blocks_per_page: list[dict[Blocks, RemovalReason]] = []
    skipped_pages: set[int] = set()  # Track page numbers that are skipped

    for page_data in pages:
        # Skip pages with too many blocks - these are likely info/inventory pages
        # with vectorized text that cause O(n²) algorithms to be very slow
        if len(page_data.blocks) > MAX_BLOCKS_PER_PAGE:
            logger.debug(
                f"Page {page_data.page_number}: skipping classification "
                f"({len(page_data.blocks)} blocks exceeds threshold of "
                f"{MAX_BLOCKS_PER_PAGE})"
            )
            skipped_pages.add(page_data.page_number)
            removed_blocks_per_page.append({})
            continue

        kept_blocks = page_data.blocks

        # Filter overlapping text blocks (e.g., "4" and "43" at same origin)
        kept_blocks, text_removed = filter_overlapping_text_blocks(kept_blocks)

        # Filter duplicate image/drawing blocks based on IOU
        kept_blocks, bbox_removed = filter_duplicate_blocks(kept_blocks)

        # Combine all removal mappings into a single dict for this page
        combined_removed_mapping = {
            **text_removed,
            **bbox_removed,
        }

        logger.debug(
            f"Page {page_data.page_number}: "
            f"filtered {len(text_removed)} overlapping text, "
            f"{len(bbox_removed)} duplicate bbox blocks"
        )

        removed_blocks_per_page.append(combined_removed_mapping)

    # Phase 2: Extract font size hints from hint pages (excluding removed blocks)
    # Build pages with non-removed blocks for hint extraction and histogram

    # Filter duplicates from hint pages (may be different from pages to classify)
    hint_pages_without_duplicates = []
    for page_data in hint_pages:
        # Skip high-block pages for hints too (same threshold)
        if len(page_data.blocks) > MAX_BLOCKS_PER_PAGE:
            continue

        # TODO We are re-filtering duplicates here; optimize by changing the API
        # to accept one list of PageData, and seperate by page_numbers.
        kept_blocks = page_data.blocks
        kept_blocks, _ = filter_overlapping_text_blocks(kept_blocks)
        kept_blocks, _ = filter_duplicate_blocks(kept_blocks)

        hint_pages_without_duplicates.append(
            PageData(
                page_number=page_data.page_number,
                bbox=page_data.bbox,
                blocks=kept_blocks,
            )
        )

    # Build pages without duplicates for classification
    pages_without_duplicates = []
    for page_data, removed_mapping in zip(pages, removed_blocks_per_page, strict=True):
        # We need to filter blocks that were removed by ANY filter
        non_removed_blocks = [
            block for block in page_data.blocks if block not in removed_mapping
        ]
        pages_without_duplicates.append(
            PageData(
                page_number=page_data.page_number,
                bbox=page_data.bbox,
                blocks=non_removed_blocks,
            )
        )

    # Generate hints from hint pages, histogram from pages to classify
    font_size_hints = FontSizeHints.from_pages(hint_pages_without_duplicates)
    page_hints = PageHintCollection.from_pages(hint_pages_without_duplicates)
    histogram = TextHistogram.from_pages(pages_without_duplicates)

    # Phase 3: Classify using the hints (on pages without duplicates)
    config = ClassifierConfig(font_size_hints=font_size_hints, page_hints=page_hints)
    classifier = Classifier(config)

    results = []
    for page_data, page_without_duplicates, removed_mapping in zip(
        pages, pages_without_duplicates, removed_blocks_per_page, strict=True
    ):
        # Handle skipped pages
        if page_data.page_number in skipped_pages:
            result = ClassificationResult(
                page_data=page_data,
                skipped_reason=(
                    f"Page has {len(page_data.blocks)} blocks, which exceeds "
                    f"the threshold of {MAX_BLOCKS_PER_PAGE}. This is likely an "
                    f"info/inventory page with vectorized text."
                ),
            )
            results.append(result)
            continue

        # Classify using only non-removed blocks
        result = classifier.classify(page_without_duplicates)

        # Update result to use original page_data (with all blocks)
        result.page_data = page_data

        # Mark removed blocks
        for removed_block, removal_reason in removed_mapping.items():
            result.mark_removed(removed_block, removal_reason)

        results.append(result)

    return BatchClassificationResult(results=results, histogram=histogram)


type Classifiers = (
    PageNumberClassifier
    | ProgressBarClassifier
    | ProgressBarIndicatorClassifier
    | PreviewClassifier
    | BackgroundClassifier
    | DividerClassifier
    | BagNumberClassifier
    | PartCountClassifier
    | PartNumberClassifier
    | StepNumberClassifier
    | StepCountClassifier
    | PieceLengthClassifier
    | ScaleClassifier
    | PartsClassifier
    | PartsListClassifier
    | PartsImageClassifier
    | ShineClassifier
    | OpenBagClassifier
    | LoosePartSymbolClassifier
    | DiagramClassifier
    | ArrowClassifier
    | SubAssemblyClassifier
    | StepClassifier
    | TriviaTextClassifier
    | PageClassifier
)


class Classifier:
    """
    Performs a single run of classification based on rules, configuration, and hints.
    This class should be stateless.
    """

    def __init__(self, config: ClassifierConfig):
        self.config = config
        # Sort classifiers topologically based on their dependencies
        self.classifiers = topological_sort(
            [
                PageNumberClassifier(config=config),
                ProgressBarIndicatorClassifier(config=config),
                ProgressBarClassifier(config=config),
                BackgroundClassifier(config=config),
                DividerClassifier(config=config),
                BagNumberClassifier(config=config),
                PartCountClassifier(config=config),
                PartNumberClassifier(config=config),
                StepNumberClassifier(config=config),
                StepCountClassifier(config=config),
                PieceLengthClassifier(config=config),
                ScaleClassifier(config=config),
                PartsClassifier(config=config),
                PartsListClassifier(config=config),
                DiagramClassifier(config=config),
                RotationSymbolClassifier(config=config),
                ArrowClassifier(config=config),
                PartsImageClassifier(config=config),
                ShineClassifier(config=config),
                OpenBagClassifier(config=config),
                LoosePartSymbolClassifier(config=config),
                PreviewClassifier(config=config),
                SubAssemblyClassifier(config=config),
                StepClassifier(config=config),
                TriviaTextClassifier(config=config),
                PageClassifier(config=config),
            ]
        )

    def classify(self, page_data: PageData) -> ClassificationResult:
        """
        Runs the classification logic and returns a result.
        It does NOT modify page_data directly.

        The classification process runs in three phases:
        1. Score all classifiers (bottom-up) - auto-registers classifiers
        2. Construct final elements (top-down starting from Page)
        """
        result = ClassificationResult(page_data=page_data)

        logger.debug(f"Starting classification for page {page_data.page_number}")

        # 1. Score all classifiers (Bottom-Up)
        # Note: score() automatically registers each classifier for its output labels
        for classifier in self.classifiers:
            classifier.score(result)

        # 2. Construct (Top-Down)
        # Find the PageClassifier to start the construction process
        page_classifier = next(
            c for c in self.classifiers if isinstance(c, PageClassifier)
        )
        page_classifier.build_all(result)

        # TODO Do we actualy ever add warnings?
        warnings = self._log_post_classification_warnings(page_data, result)
        for warning in warnings:
            result.add_warning(warning)

        return result

    def _log_post_classification_warnings(
        self, page_data: PageData, result: ClassificationResult
    ) -> list[str]:
        warnings = []

        # Check if there's a page number
        page_numbers = result.get_winners_by_score("page_number", PageNumber)
        if not page_numbers:
            warnings.append(f"Page {page_data.page_number}: missing page number")

        # Get elements by label
        parts_lists = result.get_winners_by_score("parts_list", PartsList)
        part_counts = result.get_winners_by_score("part_count", PartCount)

        for pl in parts_lists:
            inside_counts = filter_contained(part_counts, pl.bbox)
            if not inside_counts:
                warnings.append(
                    f"Page {page_data.page_number}: parts list at {pl.bbox} "
                    f"contains no part counts"
                )

        steps = result.get_winners_by_score("step_number", StepNumber)
        ABOVE_EPS = 2.0
        for step in steps:
            sb = step.bbox
            above = [pl for pl in parts_lists if pl.bbox.y1 <= sb.y0 + ABOVE_EPS]
            if not above:
                warnings.append(
                    f"Page {page_data.page_number}: step number '{step.value}' "
                    f"at {sb} has no parts list above it"
                )
        return warnings

1	"""
2	Rule-based classifier for labeling page elements.
3
4	Pipeline order and dependencies
5	--------------------------------
6	The classification pipeline operates in two main phases:
7
8	1. Bottom-up Scoring: All classifiers run independently to identify potential
9	candidates (e.g. page numbers, part counts, step numbers) and score them based
10	on heuristics. No construction of final elements happens here.
11
12	2. Top-down Construction: The root `PageClassifier` is invoked to construct
13	the final `Page` object. It recursively requests the construction of its
14	dependencies (e.g. "Give me the best PageNumber"), which in turn construct
15	their own dependencies. This ensures a consistent and validated object tree.
16
17	"""
18
19	from __future__ import annotations	1✔
20
21	import logging	1✔
22
23	from build_a_long.pdf_extract.classifier.bags import (	1✔
24	BagNumberClassifier,
25	LoosePartSymbolClassifier,
26	OpenBagClassifier,
27	)
28	from build_a_long.pdf_extract.classifier.batch_classification_result import (	1✔
29	BatchClassificationResult,
30	)
31	from build_a_long.pdf_extract.classifier.block_filter import (	1✔
32	filter_duplicate_blocks,
33	filter_overlapping_text_blocks,
34	)
35	from build_a_long.pdf_extract.classifier.classification_result import (	1✔
36	ClassificationResult,
37	)
38	from build_a_long.pdf_extract.classifier.classifier_config import ClassifierConfig	1✔
39	from build_a_long.pdf_extract.classifier.pages import (	1✔
40	PageHintCollection,
41	)
42	from build_a_long.pdf_extract.classifier.pages.background_classifier import (	1✔
43	BackgroundClassifier,
44	)
45	from build_a_long.pdf_extract.classifier.pages.divider_classifier import (	1✔
46	DividerClassifier,
47	)
48	from build_a_long.pdf_extract.classifier.pages.page_classifier import PageClassifier	1✔
49	from build_a_long.pdf_extract.classifier.pages.page_number_classifier import (	1✔
50	PageNumberClassifier,
51	)
52	from build_a_long.pdf_extract.classifier.pages.preview_classifier import (	1✔
53	PreviewClassifier,
54	)
55	from build_a_long.pdf_extract.classifier.pages.progress_bar_classifier import (	1✔
56	ProgressBarClassifier,
57	)
58	from build_a_long.pdf_extract.classifier.pages.progress_bar_indicator_classifier import (	1✔
59	ProgressBarIndicatorClassifier,
60	)
61	from build_a_long.pdf_extract.classifier.pages.trivia_text_classifier import (	1✔
62	TriviaTextClassifier,
63	)
64	from build_a_long.pdf_extract.classifier.parts import (	1✔
65	PartCountClassifier,
66	PartNumberClassifier,
67	PartsClassifier,
68	PartsImageClassifier,
69	PartsListClassifier,
70	PieceLengthClassifier,
71	ScaleClassifier,
72	ShineClassifier,
73	)
74	from build_a_long.pdf_extract.classifier.removal_reason import RemovalReason	1✔
75	from build_a_long.pdf_extract.classifier.steps import (	1✔
76	ArrowClassifier,
77	DiagramClassifier,
78	RotationSymbolClassifier,
79	StepClassifier,
80	StepCountClassifier,
81	StepNumberClassifier,
82	SubAssemblyClassifier,
83	)
84	from build_a_long.pdf_extract.classifier.text import FontSizeHints, TextHistogram	1✔
85	from build_a_long.pdf_extract.classifier.topological_sort import topological_sort	1✔
86	from build_a_long.pdf_extract.extractor import PageData	1✔
87	from build_a_long.pdf_extract.extractor.bbox import filter_contained	1✔
88	from build_a_long.pdf_extract.extractor.lego_page_elements import (	1✔
89	PageNumber,
90	PartCount,
91	PartsList,
92	StepNumber,
93	)
94	from build_a_long.pdf_extract.extractor.page_blocks import Blocks	1✔
95
96	logger = logging.getLogger(__name__)	1✔
97
98	# Pages with more blocks than this threshold will be skipped during classification.
99	# This avoids O(n²) algorithms (like duplicate detection) that become prohibitively
100	# slow on pages with thousands of vector drawings. Such pages are typically info
101	# pages where each character is a separate vector graphic.
102	# TODO: Add spatial indexing to handle high-block pages efficiently.
103	MAX_BLOCKS_PER_PAGE = 1000	1✔
104
105
106	# TODO require config, so we don't accidentally use default empty config
107	def classify_elements(	1✔
108	page: PageData, config: ClassifierConfig \| None = None
109	) -> ClassificationResult:
110	"""Classify and label elements on a single page using rule-based heuristics.
111
112	Args:
113	page: A single PageData object to classify.
114	config: Optional classifier configuration with font/page hints.
115	If None, uses default empty configuration (no hints).
116	For better classification accuracy, pass a config with
117	FontSizeHints computed from multiple pages of the same PDF.
118
119	Returns:
120	A ClassificationResult object containing the classification results.
121	"""
122	if config is None:	1✔
123	config = ClassifierConfig()	1✔
124	classifier = Classifier(config)	1✔
125
126	return classifier.classify(page)	1✔
127
128
129	def classify_pages(	1✔
130	pages: list[PageData], pages_for_hints: list[PageData] \| None = None
131	) -> BatchClassificationResult:
132	"""Classify and label elements across multiple pages using rule-based heuristics.
133
134	This function performs a three-phase process:
135	1. Filtering phase: Mark duplicate/similar blocks as removed on each page
136	2. Analysis phase: Build font size hints from text properties (excluding
137	removed blocks)
138	3. Classification phase: Use hints to guide element classification
139
140	Args:
141	pages: A list of PageData objects to classify.
142	pages_for_hints: Optional list of pages to use for generating font/page hints.
143	If None, uses `pages`. This allows generating hints from all pages
144	while only classifying a subset (e.g., when using --pages filter).
145
146	Returns:
147	BatchClassificationResult containing per-page results and global histogram
148	"""
149
150	# TODO There is a bunch of duplication in here between hints and non-hints. Refactor
151
152	# Use all pages for hint generation if provided, otherwise use selected pages
153	hint_pages = pages_for_hints if pages_for_hints is not None else pages	1✔
154
155	# Phase 1: Filter duplicate blocks on each page and track removals
156	# Skip pages with too many blocks to avoid O(n²) performance issues
157	removed_blocks_per_page: list[dict[Blocks, RemovalReason]] = []	1✔
158	skipped_pages: set[int] = set() # Track page numbers that are skipped	1✔
159
160	for page_data in pages:	1✔
161	# Skip pages with too many blocks - these are likely info/inventory pages
162	# with vectorized text that cause O(n²) algorithms to be very slow
163	if len(page_data.blocks) > MAX_BLOCKS_PER_PAGE:	1✔
164	logger.debug(	1✔
165	f"Page {page_data.page_number}: skipping classification "
166	f"({len(page_data.blocks)} blocks exceeds threshold of "
167	f"{MAX_BLOCKS_PER_PAGE})"
168	)
169	skipped_pages.add(page_data.page_number)	1✔
170	removed_blocks_per_page.append({})	1✔
171	continue	1✔
172
173	kept_blocks = page_data.blocks	1✔
174
175	# Filter overlapping text blocks (e.g., "4" and "43" at same origin)
176	kept_blocks, text_removed = filter_overlapping_text_blocks(kept_blocks)	1✔
177
178	# Filter duplicate image/drawing blocks based on IOU
179	kept_blocks, bbox_removed = filter_duplicate_blocks(kept_blocks)	1✔
180
181	# Combine all removal mappings into a single dict for this page
182	combined_removed_mapping = {	1✔
183	**text_removed,
184	**bbox_removed,
185	}
186
187	logger.debug(	1✔
188	f"Page {page_data.page_number}: "
189	f"filtered {len(text_removed)} overlapping text, "
190	f"{len(bbox_removed)} duplicate bbox blocks"
191	)
192
193	removed_blocks_per_page.append(combined_removed_mapping)	1✔
194
195	# Phase 2: Extract font size hints from hint pages (excluding removed blocks)
196	# Build pages with non-removed blocks for hint extraction and histogram
197
198	# Filter duplicates from hint pages (may be different from pages to classify)
199	hint_pages_without_duplicates = []	1✔
200	for page_data in hint_pages:	1✔
201	# Skip high-block pages for hints too (same threshold)
202	if len(page_data.blocks) > MAX_BLOCKS_PER_PAGE:	1✔
203	continue	1✔
204
205	# TODO We are re-filtering duplicates here; optimize by changing the API
206	# to accept one list of PageData, and seperate by page_numbers.
207	kept_blocks = page_data.blocks	1✔
208	kept_blocks, _ = filter_overlapping_text_blocks(kept_blocks)	1✔
209	kept_blocks, _ = filter_duplicate_blocks(kept_blocks)	1✔
210
211	hint_pages_without_duplicates.append(	1✔
212	PageData(
213	page_number=page_data.page_number,
214	bbox=page_data.bbox,
215	blocks=kept_blocks,
216	)
217	)
218
219	# Build pages without duplicates for classification
220	pages_without_duplicates = []	1✔
221	for page_data, removed_mapping in zip(pages, removed_blocks_per_page, strict=True):	1✔
222	# We need to filter blocks that were removed by ANY filter
223	non_removed_blocks = [	1✔
224	block for block in page_data.blocks if block not in removed_mapping
225	]
226	pages_without_duplicates.append(	1✔
227	PageData(
228	page_number=page_data.page_number,
229	bbox=page_data.bbox,
230	blocks=non_removed_blocks,
231	)
232	)
233
234	# Generate hints from hint pages, histogram from pages to classify
235	font_size_hints = FontSizeHints.from_pages(hint_pages_without_duplicates)	1✔
236	page_hints = PageHintCollection.from_pages(hint_pages_without_duplicates)	1✔
237	histogram = TextHistogram.from_pages(pages_without_duplicates)	1✔
238
239	# Phase 3: Classify using the hints (on pages without duplicates)
240	config = ClassifierConfig(font_size_hints=font_size_hints, page_hints=page_hints)	1✔
241	classifier = Classifier(config)	1✔
242
243	results = []	1✔
244	for page_data, page_without_duplicates, removed_mapping in zip(	1✔
245	pages, pages_without_duplicates, removed_blocks_per_page, strict=True
246	):
247	# Handle skipped pages
248	if page_data.page_number in skipped_pages:	1✔
249	result = ClassificationResult(	1✔
250	page_data=page_data,
251	skipped_reason=(
252	f"Page has {len(page_data.blocks)} blocks, which exceeds "
253	f"the threshold of {MAX_BLOCKS_PER_PAGE}. This is likely an "
254	f"info/inventory page with vectorized text."
255	),
256	)
257	results.append(result)	1✔
258	continue	1✔
259
260	# Classify using only non-removed blocks
261	result = classifier.classify(page_without_duplicates)	1✔
262
263	# Update result to use original page_data (with all blocks)
264	result.page_data = page_data	1✔
265
266	# Mark removed blocks
267	for removed_block, removal_reason in removed_mapping.items():	1✔
268	result.mark_removed(removed_block, removal_reason)	1✔
269
270	results.append(result)	1✔
271
272	return BatchClassificationResult(results=results, histogram=histogram)	1✔
273
274
275	type Classifiers = (	1✔
276	PageNumberClassifier
277	\| ProgressBarClassifier
278	\| ProgressBarIndicatorClassifier
279	\| PreviewClassifier
280	\| BackgroundClassifier
281	\| DividerClassifier
282	\| BagNumberClassifier
283	\| PartCountClassifier
284	\| PartNumberClassifier
285	\| StepNumberClassifier
286	\| StepCountClassifier
287	\| PieceLengthClassifier
288	\| ScaleClassifier
289	\| PartsClassifier
290	\| PartsListClassifier
291	\| PartsImageClassifier
292	\| ShineClassifier
293	\| OpenBagClassifier
294	\| LoosePartSymbolClassifier
295	\| DiagramClassifier
296	\| ArrowClassifier
297	\| SubAssemblyClassifier
298	\| StepClassifier
299	\| TriviaTextClassifier
300	\| PageClassifier
301	)
302
303
304	class Classifier:	1✔
305	"""
306	Performs a single run of classification based on rules, configuration, and hints.
307	This class should be stateless.
308	"""
309
310	def __init__(self, config: ClassifierConfig):	1✔
311	self.config = config	1✔
312	# Sort classifiers topologically based on their dependencies
313	self.classifiers = topological_sort(	1✔
314	[
315	PageNumberClassifier(config=config),
316	ProgressBarIndicatorClassifier(config=config),
317	ProgressBarClassifier(config=config),
318	BackgroundClassifier(config=config),
319	DividerClassifier(config=config),
320	BagNumberClassifier(config=config),
321	PartCountClassifier(config=config),
322	PartNumberClassifier(config=config),
323	StepNumberClassifier(config=config),
324	StepCountClassifier(config=config),
325	PieceLengthClassifier(config=config),
326	ScaleClassifier(config=config),
327	PartsClassifier(config=config),
328	PartsListClassifier(config=config),
329	DiagramClassifier(config=config),
330	RotationSymbolClassifier(config=config),
331	ArrowClassifier(config=config),
332	PartsImageClassifier(config=config),
333	ShineClassifier(config=config),
334	OpenBagClassifier(config=config),
335	LoosePartSymbolClassifier(config=config),
336	PreviewClassifier(config=config),
337	SubAssemblyClassifier(config=config),
338	StepClassifier(config=config),
339	TriviaTextClassifier(config=config),
340	PageClassifier(config=config),
341	]
342	)
343
344	def classify(self, page_data: PageData) -> ClassificationResult:	1✔
345	"""
346	Runs the classification logic and returns a result.
347	It does NOT modify page_data directly.
348
349	The classification process runs in three phases:
350	1. Score all classifiers (bottom-up) - auto-registers classifiers
351	2. Construct final elements (top-down starting from Page)
352	"""
353	result = ClassificationResult(page_data=page_data)	1✔
354
355	logger.debug(f"Starting classification for page {page_data.page_number}")	1✔
356
357	# 1. Score all classifiers (Bottom-Up)
358	# Note: score() automatically registers each classifier for its output labels
359	for classifier in self.classifiers:	1✔
360	classifier.score(result)	1✔
361
362	# 2. Construct (Top-Down)
363	# Find the PageClassifier to start the construction process
364	page_classifier = next(	1✔
365	c for c in self.classifiers if isinstance(c, PageClassifier)
366	)
367	page_classifier.build_all(result)	1✔
368
369	# TODO Do we actualy ever add warnings?
370	warnings = self._log_post_classification_warnings(page_data, result)	1✔
371	for warning in warnings:	1✔
372	result.add_warning(warning)	1✔
373
374	return result	1✔
375
376	def _log_post_classification_warnings(	1✔
377	self, page_data: PageData, result: ClassificationResult
378	) -> list[str]:
379	warnings = []	1✔
380
381	# Check if there's a page number
382	page_numbers = result.get_winners_by_score("page_number", PageNumber)	1✔
383	if not page_numbers:	1✔
384	warnings.append(f"Page {page_data.page_number}: missing page number")	1✔
385
386	# Get elements by label
387	parts_lists = result.get_winners_by_score("parts_list", PartsList)	1✔
388	part_counts = result.get_winners_by_score("part_count", PartCount)	1✔
389
390	for pl in parts_lists:	1✔
391	inside_counts = filter_contained(part_counts, pl.bbox)	1✔
392	if not inside_counts:	1✔
393	warnings.append(	×
394	f"Page {page_data.page_number}: parts list at {pl.bbox} "
395	f"contains no part counts"
396	)
397
398	steps = result.get_winners_by_score("step_number", StepNumber)	1✔
399	ABOVE_EPS = 2.0	1✔
400	for step in steps:	1✔
401	sb = step.bbox	1✔
402	above = [pl for pl in parts_lists if pl.bbox.y1 <= sb.y0 + ABOVE_EPS]	1✔
403	if not above:	1✔
404	warnings.append(	1✔
405	f"Page {page_data.page_number}: step number '{step.value}' "
406	f"at {sb} has no parts list above it"
407	)
408	return warnings	1✔

bramp / build-along / 20158146015

Source File Press 'n' to go to next uncovered line, 'b' for previous

Source File
Press 'n' to go to next uncovered line, 'b' for previous