PyPI - complydoc - Versions diffs - 0.3.0__tar.gz - Mend

complydoc 0.3.0__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (172) hide show

complydoc-0.3.0/.github/images/complydoc-architecture-dark.html +148 -0
complydoc-0.3.0/.github/images/complydoc-architecture-dark.svg +123 -0
complydoc-0.3.0/.github/images/complydoc-architecture.html +148 -0
complydoc-0.3.0/.github/images/complydoc-architecture.svg +123 -0
complydoc-0.3.0/.github/images/logo-dark.svg +13 -0
complydoc-0.3.0/.github/images/logo-light.svg +13 -0
complydoc-0.3.0/.github/images/report-dark.png +0 -0
complydoc-0.3.0/.github/images/report-light.png +0 -0
complydoc-0.3.0/.github/workflows/checks.yml +91 -0
complydoc-0.3.0/.github/workflows/publish.yml +73 -0
complydoc-0.3.0/.github/workflows/release.yml +127 -0
complydoc-0.3.0/.gitignore +32 -0
complydoc-0.3.0/.python-version +1 -0
complydoc-0.3.0/CONTRIBUTING.md +190 -0
complydoc-0.3.0/LICENSE +21 -0
complydoc-0.3.0/Makefile +145 -0
complydoc-0.3.0/PKG-INFO +362 -0
complydoc-0.3.0/README.md +316 -0
complydoc-0.3.0/pyproject.toml +134 -0
complydoc-0.3.0/scripts/build_diagram.py +211 -0
complydoc-0.3.0/scripts/build_price_table.py +202 -0
complydoc-0.3.0/scripts/build_sbom.py +93 -0
complydoc-0.3.0/src/complydoc/CHANGELOG.md +347 -0
complydoc-0.3.0/src/complydoc/__init__.py +6 -0
complydoc-0.3.0/src/complydoc/audit.py +467 -0
complydoc-0.3.0/src/complydoc/cli.py +1148 -0
complydoc-0.3.0/src/complydoc/config/__init__.py +0 -0
complydoc-0.3.0/src/complydoc/config/loader.py +335 -0
complydoc-0.3.0/src/complydoc/config/model_prices.json +1628 -0
complydoc-0.3.0/src/complydoc/config/pricing.yaml +264 -0
complydoc-0.3.0/src/complydoc/config/readiness.yaml +230 -0
complydoc-0.3.0/src/complydoc/config/schema.py +406 -0
complydoc-0.3.0/src/complydoc/config/sensitive.yaml +371 -0
complydoc-0.3.0/src/complydoc/cost/__init__.py +0 -0
complydoc-0.3.0/src/complydoc/cost/estimator.py +387 -0
complydoc-0.3.0/src/complydoc/cost/price_table.py +192 -0
complydoc-0.3.0/src/complydoc/cost/pricing_import.py +241 -0
complydoc-0.3.0/src/complydoc/cost/tokenizer.py +89 -0
complydoc-0.3.0/src/complydoc/cost/vision.py +106 -0
complydoc-0.3.0/src/complydoc/discovery.py +68 -0
complydoc-0.3.0/src/complydoc/geometry.py +40 -0
complydoc-0.3.0/src/complydoc/ingest/__init__.py +0 -0
complydoc-0.3.0/src/complydoc/ingest/base.py +290 -0
complydoc-0.3.0/src/complydoc/ingest/docx.py +146 -0
complydoc-0.3.0/src/complydoc/ingest/engines/__init__.py +0 -0
complydoc-0.3.0/src/complydoc/ingest/engines/base.py +46 -0
complydoc-0.3.0/src/complydoc/ingest/engines/rapidocr.py +104 -0
complydoc-0.3.0/src/complydoc/ingest/engines/registry.py +53 -0
complydoc-0.3.0/src/complydoc/ingest/engines/tesseract.py +75 -0
complydoc-0.3.0/src/complydoc/ingest/extractors/__init__.py +0 -0
complydoc-0.3.0/src/complydoc/ingest/extractors/base.py +110 -0
complydoc-0.3.0/src/complydoc/ingest/extractors/pdfium.py +65 -0
complydoc-0.3.0/src/complydoc/ingest/extractors/plumber.py +53 -0
complydoc-0.3.0/src/complydoc/ingest/extractors/pypdfreader.py +47 -0
complydoc-0.3.0/src/complydoc/ingest/extractors/registry.py +58 -0
complydoc-0.3.0/src/complydoc/ingest/image.py +92 -0
complydoc-0.3.0/src/complydoc/ingest/ocr.py +126 -0
complydoc-0.3.0/src/complydoc/ingest/pdf.py +697 -0
complydoc-0.3.0/src/complydoc/ingest/registry.py +55 -0
complydoc-0.3.0/src/complydoc/ingest/xlsx.py +90 -0
complydoc-0.3.0/src/complydoc/offline.py +97 -0
complydoc-0.3.0/src/complydoc/overall.py +254 -0
complydoc-0.3.0/src/complydoc/quickwins.py +299 -0
complydoc-0.3.0/src/complydoc/readiness/__init__.py +0 -0
complydoc-0.3.0/src/complydoc/readiness/analyser.py +116 -0
complydoc-0.3.0/src/complydoc/readiness/base.py +89 -0
complydoc-0.3.0/src/complydoc/readiness/registry.py +52 -0
complydoc-0.3.0/src/complydoc/readiness/scoring.py +120 -0
complydoc-0.3.0/src/complydoc/readiness/signals/__init__.py +0 -0
complydoc-0.3.0/src/complydoc/readiness/signals/acroform.py +23 -0
complydoc-0.3.0/src/complydoc/readiness/signals/columns.py +75 -0
complydoc-0.3.0/src/complydoc/readiness/signals/date_formats.py +60 -0
complydoc-0.3.0/src/complydoc/readiness/signals/encryption.py +31 -0
complydoc-0.3.0/src/complydoc/readiness/signals/fonts.py +59 -0
complydoc-0.3.0/src/complydoc/readiness/signals/garbled.py +75 -0
complydoc-0.3.0/src/complydoc/readiness/signals/image_area.py +38 -0
complydoc-0.3.0/src/complydoc/readiness/signals/language.py +73 -0
complydoc-0.3.0/src/complydoc/readiness/signals/ocr_confidence.py +38 -0
complydoc-0.3.0/src/complydoc/readiness/signals/page_size.py +32 -0
complydoc-0.3.0/src/complydoc/readiness/signals/rotation_skew.py +198 -0
complydoc-0.3.0/src/complydoc/readiness/signals/scan_dpi.py +50 -0
complydoc-0.3.0/src/complydoc/readiness/signals/tables.py +124 -0
complydoc-0.3.0/src/complydoc/readiness/signals/text_coverage.py +38 -0
complydoc-0.3.0/src/complydoc/readiness/signals/text_layer.py +35 -0
complydoc-0.3.0/src/complydoc/report/__init__.py +0 -0
complydoc-0.3.0/src/complydoc/report/charts.py +339 -0
complydoc-0.3.0/src/complydoc/report/diffing.py +108 -0
complydoc-0.3.0/src/complydoc/report/html_writer.py +394 -0
complydoc-0.3.0/src/complydoc/report/json_writer.py +24 -0
complydoc-0.3.0/src/complydoc/report/limitations.py +385 -0
complydoc-0.3.0/src/complydoc/report/models.py +400 -0
complydoc-0.3.0/src/complydoc/report/preview.py +379 -0
complydoc-0.3.0/src/complydoc/report/templates/report.html.j2 +1732 -0
complydoc-0.3.0/src/complydoc/report/text_writer.py +69 -0
complydoc-0.3.0/src/complydoc/sample/employee-record.pdf +0 -0
complydoc-0.3.0/src/complydoc/sample/financial-summary.pdf +0 -0
complydoc-0.3.0/src/complydoc/sample/invoice-scan.pdf +79 -0
complydoc-0.3.0/src/complydoc/sample/supplier-list.docx +0 -0
complydoc-0.3.0/src/complydoc/sample/supplier-onboarding.pdf +0 -0
complydoc-0.3.0/src/complydoc/sample/terms-and-conditions.pdf +0 -0
complydoc-0.3.0/src/complydoc/sampling.py +78 -0
complydoc-0.3.0/src/complydoc/sensitive/__init__.py +0 -0
complydoc-0.3.0/src/complydoc/sensitive/base.py +125 -0
complydoc-0.3.0/src/complydoc/sensitive/detectors/__init__.py +0 -0
complydoc-0.3.0/src/complydoc/sensitive/detectors/ner.py +113 -0
complydoc-0.3.0/src/complydoc/sensitive/detectors/regex_detector.py +68 -0
complydoc-0.3.0/src/complydoc/sensitive/masking.py +60 -0
complydoc-0.3.0/src/complydoc/sensitive/registry.py +59 -0
complydoc-0.3.0/src/complydoc/sensitive/scanner.py +224 -0
complydoc-0.3.0/src/complydoc/sensitive/validators.py +313 -0
complydoc-0.3.0/src/complydoc/skill/SKILL.md +122 -0
complydoc-0.3.0/src/complydoc/skill/__init__.py +0 -0
complydoc-0.3.0/src/complydoc/text.py +96 -0
complydoc-0.3.0/src/complydoc/vendor/__init__.py +14 -0
complydoc-0.3.0/src/complydoc/vendor/tiktoken_cache/9b5ad71b2ce5302211f9c61530b329a4922fc6a4 +100256 -0
complydoc-0.3.0/src/complydoc/vendor/tiktoken_cache/fb374d419588a4632f3f557e76b4b70aebbca790 +199998 -0
complydoc-0.3.0/src/complydoc/warm.py +44 -0
complydoc-0.3.0/tests/__init__.py +0 -0
complydoc-0.3.0/tests/conftest.py +36 -0
complydoc-0.3.0/tests/fixtures/acroform.pdf +0 -0
complydoc-0.3.0/tests/fixtures/broken.pdf +3 -0
complydoc-0.3.0/tests/fixtures/dense_text.pdf +0 -0
complydoc-0.3.0/tests/fixtures/encrypted.pdf +0 -0
complydoc-0.3.0/tests/fixtures/garbled.pdf +0 -0
complydoc-0.3.0/tests/fixtures/merged_header_table.pdf +0 -0
complydoc-0.3.0/tests/fixtures/mixed_page_sizes.pdf +0 -0
complydoc-0.3.0/tests/fixtures/native_text.pdf +0 -0
complydoc-0.3.0/tests/fixtures/notes.txt +1 -0
complydoc-0.3.0/tests/fixtures/rotated_scan.pdf +96 -0
complydoc-0.3.0/tests/fixtures/sample.docx +0 -0
complydoc-0.3.0/tests/fixtures/sample.xlsx +0 -0
complydoc-0.3.0/tests/fixtures/scan_page.png +0 -0
complydoc-0.3.0/tests/fixtures/scanned_page.pdf +79 -0
complydoc-0.3.0/tests/fixtures/sensitive_sample.pdf +0 -0
complydoc-0.3.0/tests/fixtures/two_column.pdf +0 -0
complydoc-0.3.0/tests/fixtures/whitespace_table.pdf +0 -0
complydoc-0.3.0/tests/generate_fixtures.py +568 -0
complydoc-0.3.0/tests/helpers.py +22 -0
complydoc-0.3.0/tests/test_charts.py +110 -0
complydoc-0.3.0/tests/test_cli.py +387 -0
complydoc-0.3.0/tests/test_config.py +124 -0
complydoc-0.3.0/tests/test_cost.py +178 -0
complydoc-0.3.0/tests/test_diffing.py +97 -0
complydoc-0.3.0/tests/test_engines.py +92 -0
complydoc-0.3.0/tests/test_extractors.py +260 -0
complydoc-0.3.0/tests/test_ingest.py +161 -0
complydoc-0.3.0/tests/test_limitations.py +131 -0
complydoc-0.3.0/tests/test_offline_guard.py +59 -0
complydoc-0.3.0/tests/test_overall.py +92 -0
complydoc-0.3.0/tests/test_pageview.py +257 -0
complydoc-0.3.0/tests/test_parallel.py +153 -0
complydoc-0.3.0/tests/test_preview.py +317 -0
complydoc-0.3.0/tests/test_price_table.py +230 -0
complydoc-0.3.0/tests/test_pricing_import.py +209 -0
complydoc-0.3.0/tests/test_progress.py +75 -0
complydoc-0.3.0/tests/test_quickwins.py +83 -0
complydoc-0.3.0/tests/test_readings.py +194 -0
complydoc-0.3.0/tests/test_report.py +528 -0
complydoc-0.3.0/tests/test_sampling.py +65 -0
complydoc-0.3.0/tests/test_security_order.py +83 -0
complydoc-0.3.0/tests/test_sensitive/__init__.py +0 -0
complydoc-0.3.0/tests/test_sensitive/test_evidence.py +90 -0
complydoc-0.3.0/tests/test_sensitive/test_masking.py +69 -0
complydoc-0.3.0/tests/test_sensitive/test_scanner.py +154 -0
complydoc-0.3.0/tests/test_sensitive/test_validators.py +161 -0
complydoc-0.3.0/tests/test_signals/__init__.py +0 -0
complydoc-0.3.0/tests/test_signals/test_awkward_documents.py +193 -0
complydoc-0.3.0/tests/test_signals/test_ocr_confidence.py +38 -0
complydoc-0.3.0/tests/test_signals/test_tables.py +63 -0
complydoc-0.3.0/tests/test_timing.py +117 -0
complydoc-0.3.0/tests/test_warm.py +40 -0
complydoc-0.3.0/uv.lock +2420 -0

complydoc-0.3.0/.github/images/complydoc-architecture-dark.html ADDED Viewed

@@ -0,0 +1,148 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="utf-8">
+<meta name="viewport" content="width=device-width, initial-scale=1">
+<title>complydoc — pipeline architecture</title>
+<link href="https://fonts.googleapis.com/css2?family=Instrument+Serif:ital@0;1&family=Geist:wght@400;500;600&family=Geist+Mono:wght@400;500;600&display=swap" rel="stylesheet">
+<style>
+  body { margin:0; background:#22272e; color:#f5f5f5;
+    font-family:'Geist',sans-serif; padding:3rem 2rem; }
+  .wrap { max-width:1080px; margin:0 auto; }
+  .eyebrow { font-family:'Geist Mono',monospace; font-size:8px; letter-spacing:0.14em;
+    text-transform:uppercase; color:#8e98ac; margin:0 0 0.5rem; }
+  h1 { font-family:'Instrument Serif',serif; font-weight:400; font-size:1.75rem;
+    margin:0 0 0.25rem; }
+  .sub { color:#bfc0c0; font-size:0.875rem; margin:0 0 2rem; max-width:64ch; }
+  svg { width:100%; height:auto; display:block; }
+</style>
+</head>
+<body>
+<div class="wrap">
+  <p class="eyebrow">complydoc</p>
+  <h1>Pipeline</h1>
+  <p class="sub">Files are read locally by per-format loaders, then passed to three analysis
+  components that run independently. Each run writes a JSON report and an HTML report.</p>
+  <svg viewBox="0 0 1000 600" role="img" aria-labelledby="complydoc-architecture-dark-title complydoc-architecture-dark-desc" xmlns="http://www.w3.org/2000/svg">
+  <title id="complydoc-architecture-dark-title">complydoc pipeline architecture</title>
+  <desc id="complydoc-architecture-dark-desc">A folder of documents passes through discovery and a format-specific ingest layer into three independent analysis components — cost, difficulty and sensitive data — which are driven by YAML config and emit a diffable JSON report and a self-contained HTML report. The whole pipeline sits inside a network guard boundary, so no document content can leave the machine.</desc>
+  <defs>
+    <marker id="complydoc-architecture-dark-arrow" markerWidth="8" markerHeight="6" refX="7" refY="3" orient="auto">
+      <polygon points="0 0, 8 3, 0 6" fill="#bfc0c0"/>
+    </marker>
+    <marker id="complydoc-architecture-dark-arrow-accent" markerWidth="8" markerHeight="6" refX="7" refY="3" orient="auto">
+      <polygon points="0 0, 8 3, 0 6" fill="#2fa96a"/>
+    </marker>
+  </defs>
+  <rect width="100%" height="100%" fill="#22272e"/>
+  <!-- Network guard boundary: drawn first, behind everything -->
+  <rect x="24" y="72" width="940" height="440" rx="8" fill="rgba(47,169,106,0.05)" stroke="rgba(47,169,106,0.60)" stroke-width="1" stroke-dasharray="4,4"/>
+  <rect x="44" y="64" width="96" height="16" rx="2" fill="#22272e"/>
+  <text x="52" y="76" fill="#2fa96a" font-size="8" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" letter-spacing="0.14em">NETWORK GUARD</text>
+  <!-- Analysis zone -->
+  <rect x="560" y="112" width="208" height="296" rx="8" fill="rgba(245,245,245,0.03)" stroke="rgba(245,245,245,0.12)" stroke-width="0.8"/>
+  <rect x="596" y="104" width="136" height="16" rx="2" fill="#22272e"/>
+  <text x="664" y="116" fill="rgba(245,245,245,0.45)" font-size="7" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" text-anchor="middle" letter-spacing="0.14em">ANALYSIS · INDEPENDENT</text>
+  <!-- Arrows, drawn before boxes -->
+  <line x1="184" y1="272" x2="216" y2="272" stroke="#bfc0c0" stroke-width="1.2" marker-end="url(#complydoc-architecture-dark-arrow)"/>
+  <line x1="352" y1="272" x2="384" y2="272" stroke="#bfc0c0" stroke-width="1.2" marker-end="url(#complydoc-architecture-dark-arrow)"/>
+  <path d="M 528,252 H 544 Q 552,252 552,244 V 184 Q 552,176 560,176 H 576" fill="none" stroke="#bfc0c0" stroke-width="1.2" marker-end="url(#complydoc-architecture-dark-arrow)"/>
+  <line x1="528" y1="272" x2="576" y2="272" stroke="#bfc0c0" stroke-width="1.2" marker-end="url(#complydoc-architecture-dark-arrow)"/>
+  <path d="M 528,292 H 544 Q 552,292 552,300 V 360 Q 552,368 560,368 H 576" fill="none" stroke="#bfc0c0" stroke-width="1.2" marker-end="url(#complydoc-architecture-dark-arrow)"/>
+  <line x1="664" y1="448" x2="664" y2="408" stroke="#bfc0c0" stroke-width="1.2" stroke-dasharray="4,3" marker-end="url(#complydoc-architecture-dark-arrow)"/>
+  <rect x="676" y="420" width="84" height="12" rx="2" fill="#22272e"/>
+  <text x="680" y="429" fill="#8e98ac" font-size="8" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" letter-spacing="0.06em">THRESHOLDS</text>
+  <line x1="768" y1="240" x2="804" y2="240" stroke="#bfc0c0" stroke-width="1.2" marker-end="url(#complydoc-architecture-dark-arrow)"/>
+  <path d="M 768,300 H 778 Q 786,300 786,308 V 328 Q 786,336 794,336 H 804" fill="none" stroke="#bfc0c0" stroke-width="1.2" marker-end="url(#complydoc-architecture-dark-arrow)"/>
+  <!-- Nodes -->
+  <rect x="48" y="240" width="136" height="64" rx="6" fill="#22272e"/>
+  <rect x="48" y="240" width="136" height="64" rx="6" fill="rgba(191,192,192,0.10)" stroke="#8e98ac" stroke-width="1"/>
+  <rect x="60" y="250" width="36" height="12" rx="2" fill="none" stroke="#8e98ac" stroke-opacity="0.40" stroke-width="0.8"/>
+  <text x="78.0" y="259" fill="#8e98ac" fill-opacity="0.85" font-size="7" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" text-anchor="middle" letter-spacing="0.08em">INPUT</text>
+  <text x="116.0" y="280.0" fill="#f5f5f5" font-size="12" font-weight="600" font-family="'Geist', 'Helvetica Neue', Helvetica, Arial, sans-serif" text-anchor="middle">documents/</text>
+  <text x="116.0" y="296.0" fill="#8e98ac" font-size="9" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" text-anchor="middle">pdf · img · docx · xlsx</text>
+  <rect x="216" y="240" width="136" height="64" rx="6" fill="#22272e"/>
+  <rect x="216" y="240" width="136" height="64" rx="6" fill="#2c323b" stroke="#f5f5f5" stroke-width="1"/>
+  <rect x="228" y="250" width="32" height="12" rx="2" fill="none" stroke="#f5f5f5" stroke-opacity="0.40" stroke-width="0.8"/>
+  <text x="244.0" y="259" fill="#f5f5f5" fill-opacity="0.85" font-size="7" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" text-anchor="middle" letter-spacing="0.08em">WALK</text>
+  <text x="284.0" y="280.0" fill="#f5f5f5" font-size="12" font-weight="600" font-family="'Geist', 'Helvetica Neue', Helvetica, Arial, sans-serif" text-anchor="middle">Discovery</text>
+  <text x="284.0" y="296.0" fill="#8e98ac" font-size="9" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" text-anchor="middle">skips unopenable</text>
+  <rect x="384" y="240" width="144" height="64" rx="6" fill="#22272e"/>
+  <rect x="384" y="240" width="144" height="64" rx="6" fill="#2c323b" stroke="#f5f5f5" stroke-width="1"/>
+  <rect x="396" y="250" width="32" height="12" rx="2" fill="none" stroke="#f5f5f5" stroke-opacity="0.40" stroke-width="0.8"/>
+  <text x="412.0" y="259" fill="#f5f5f5" fill-opacity="0.85" font-size="7" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" text-anchor="middle" letter-spacing="0.08em">LOAD</text>
+  <text x="456.0" y="280.0" fill="#f5f5f5" font-size="12" font-weight="600" font-family="'Geist', 'Helvetica Neue', Helvetica, Arial, sans-serif" text-anchor="middle">Ingest</text>
+  <text x="456.0" y="296.0" fill="#8e98ac" font-size="9" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" text-anchor="middle">per-format loaders</text>
+  <rect x="576" y="144" width="176" height="64" rx="6" fill="#22272e"/>
+  <rect x="576" y="144" width="176" height="64" rx="6" fill="#2c323b" stroke="#f5f5f5" stroke-width="1"/>
+  <rect x="588" y="154" width="20" height="12" rx="2" fill="none" stroke="#f5f5f5" stroke-opacity="0.40" stroke-width="0.8"/>
+  <text x="598.0" y="163" fill="#f5f5f5" fill-opacity="0.85" font-size="7" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" text-anchor="middle" letter-spacing="0.08em">01</text>
+  <text x="664.0" y="184.0" fill="#f5f5f5" font-size="12" font-weight="600" font-family="'Geist', 'Helvetica Neue', Helvetica, Arial, sans-serif" text-anchor="middle">Cost</text>
+  <text x="664.0" y="200.0" fill="#8e98ac" font-size="9" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" text-anchor="middle">tokens, pages, price</text>
+  <rect x="576" y="240" width="176" height="64" rx="6" fill="#22272e"/>
+  <rect x="576" y="240" width="176" height="64" rx="6" fill="#2c323b" stroke="#f5f5f5" stroke-width="1"/>
+  <rect x="588" y="250" width="20" height="12" rx="2" fill="none" stroke="#f5f5f5" stroke-opacity="0.40" stroke-width="0.8"/>
+  <text x="598.0" y="259" fill="#f5f5f5" fill-opacity="0.85" font-size="7" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" text-anchor="middle" letter-spacing="0.08em">02</text>
+  <text x="664.0" y="280.0" fill="#f5f5f5" font-size="12" font-weight="600" font-family="'Geist', 'Helvetica Neue', Helvetica, Arial, sans-serif" text-anchor="middle">Difficulty</text>
+  <text x="664.0" y="296.0" fill="#8e98ac" font-size="9" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" text-anchor="middle">18 measured signals</text>
+  <rect x="576" y="336" width="176" height="64" rx="6" fill="#22272e"/>
+  <rect x="576" y="336" width="176" height="64" rx="6" fill="rgba(47,169,106,0.14)" stroke="#2fa96a" stroke-width="1"/>
+  <rect x="588" y="346" width="20" height="12" rx="2" fill="none" stroke="#2fa96a" stroke-opacity="0.40" stroke-width="0.8"/>
+  <text x="598.0" y="355" fill="#2fa96a" fill-opacity="0.85" font-size="7" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" text-anchor="middle" letter-spacing="0.08em">03</text>
+  <text x="664.0" y="376.0" fill="#f5f5f5" font-size="12" font-weight="600" font-family="'Geist', 'Helvetica Neue', Helvetica, Arial, sans-serif" text-anchor="middle">Sensitive</text>
+  <text x="664.0" y="392.0" fill="#8e98ac" font-size="9" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" text-anchor="middle">masked by default</text>
+  <rect x="576" y="448" width="176" height="52" rx="6" fill="#22272e"/>
+  <rect x="576" y="448" width="176" height="52" rx="6" fill="rgba(245,245,245,0.06)" stroke="#bfc0c0" stroke-width="1"/>
+  <rect x="588" y="458" width="32" height="12" rx="2" fill="none" stroke="#bfc0c0" stroke-opacity="0.40" stroke-width="0.8"/>
+  <text x="604.0" y="467" fill="#bfc0c0" fill-opacity="0.85" font-size="7" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" text-anchor="middle" letter-spacing="0.08em">YAML</text>
+  <text x="664.0" y="482.0" fill="#f5f5f5" font-size="12" font-weight="600" font-family="'Geist', 'Helvetica Neue', Helvetica, Arial, sans-serif" text-anchor="middle">Config</text>
+  <text x="664.0" y="498.0" fill="#8e98ac" font-size="9" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" text-anchor="middle">prices · weights · patterns</text>
+  <rect x="804" y="208" width="136" height="64" rx="6" fill="#22272e"/>
+  <rect x="804" y="208" width="136" height="64" rx="6" fill="rgba(245,245,245,0.06)" stroke="#bfc0c0" stroke-width="1"/>
+  <rect x="816" y="218" width="32" height="12" rx="2" fill="none" stroke="#bfc0c0" stroke-opacity="0.40" stroke-width="0.8"/>
+  <text x="832.0" y="227" fill="#bfc0c0" fill-opacity="0.85" font-size="7" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" text-anchor="middle" letter-spacing="0.08em">JSON</text>
+  <text x="872.0" y="248.0" fill="#f5f5f5" font-size="12" font-weight="600" font-family="'Geist', 'Helvetica Neue', Helvetica, Arial, sans-serif" text-anchor="middle">report.json</text>
+  <text x="872.0" y="264.0" fill="#8e98ac" font-size="9" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" text-anchor="middle">machine readable</text>
+  <rect x="804" y="304" width="136" height="64" rx="6" fill="#22272e"/>
+  <rect x="804" y="304" width="136" height="64" rx="6" fill="rgba(245,245,245,0.06)" stroke="#bfc0c0" stroke-width="1"/>
+  <rect x="816" y="314" width="32" height="12" rx="2" fill="none" stroke="#bfc0c0" stroke-opacity="0.40" stroke-width="0.8"/>
+  <text x="832.0" y="323" fill="#bfc0c0" fill-opacity="0.85" font-size="7" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" text-anchor="middle" letter-spacing="0.08em">HTML</text>
+  <text x="872.0" y="344.0" fill="#f5f5f5" font-size="12" font-weight="600" font-family="'Geist', 'Helvetica Neue', Helvetica, Arial, sans-serif" text-anchor="middle">report.html</text>
+  <text x="872.0" y="360.0" fill="#8e98ac" font-size="9" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" text-anchor="middle">self-contained</text>
+  <!-- Legend -->
+  <line x1="24" y1="544" x2="976" y2="544" stroke="rgba(245,245,245,0.14)" stroke-width="0.8"/>
+  <text x="24" y="566" fill="#bfc0c0" font-size="8" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" letter-spacing="0.14em">LEGEND</text>
+  <rect x="112" y="556" width="14" height="12" rx="2" fill="rgba(47,169,106,0.14)" stroke="#2fa96a" stroke-width="1"/>
+  <text x="134" y="566" fill="#8e98ac" font-size="8" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace">MASKED VALUES</text>
+  <rect x="356" y="556" width="14" height="12" rx="2" fill="rgba(47,169,106,0.05)" stroke="rgba(47,169,106,0.60)" stroke-width="1" stroke-dasharray="3,3"/>
+  <text x="378" y="566" fill="#8e98ac" font-size="8" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace">NO OUTBOUND SOCKET</text>
+  <rect x="592" y="556" width="14" height="12" rx="2" fill="#2c323b" stroke="#f5f5f5" stroke-width="1"/>
+  <text x="614" y="566" fill="#8e98ac" font-size="8" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace">PIPELINE STAGE</text>
+  <rect x="792" y="556" width="14" height="12" rx="2" fill="rgba(245,245,245,0.06)" stroke="#bfc0c0" stroke-width="1"/>
+  <text x="814" y="566" fill="#8e98ac" font-size="8" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace">CONFIG AND OUTPUT</text>
+</svg>
+</div>
+</body>
+</html>

complydoc-0.3.0/.github/images/complydoc-architecture-dark.svg ADDED Viewed

@@ -0,0 +1,123 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<svg viewBox="0 0 1000 600" role="img" aria-labelledby="complydoc-architecture-dark-title complydoc-architecture-dark-desc" xmlns="http://www.w3.org/2000/svg">
+  <title id="complydoc-architecture-dark-title">complydoc pipeline architecture</title>
+  <desc id="complydoc-architecture-dark-desc">A folder of documents passes through discovery and a format-specific ingest layer into three independent analysis components — cost, difficulty and sensitive data — which are driven by YAML config and emit a diffable JSON report and a self-contained HTML report. The whole pipeline sits inside a network guard boundary, so no document content can leave the machine.</desc>
+  <defs>
+    <style>@import url('https://fonts.googleapis.com/css2?family=Instrument+Serif:ital@0;1&amp;family=Geist:wght@400;500;600&amp;family=Geist+Mono:wght@400;500;600&amp;display=swap');</style>
+    <marker id="complydoc-architecture-dark-arrow" markerWidth="8" markerHeight="6" refX="7" refY="3" orient="auto">
+      <polygon points="0 0, 8 3, 0 6" fill="#bfc0c0"/>
+    </marker>
+    <marker id="complydoc-architecture-dark-arrow-accent" markerWidth="8" markerHeight="6" refX="7" refY="3" orient="auto">
+      <polygon points="0 0, 8 3, 0 6" fill="#2fa96a"/>
+    </marker>
+  </defs>
+  <rect width="100%" height="100%" fill="#22272e"/>
+  <!-- Network guard boundary: drawn first, behind everything -->
+  <rect x="24" y="72" width="940" height="440" rx="8" fill="rgba(47,169,106,0.05)" stroke="rgba(47,169,106,0.60)" stroke-width="1" stroke-dasharray="4,4"/>
+  <rect x="44" y="64" width="96" height="16" rx="2" fill="#22272e"/>
+  <text x="52" y="76" fill="#2fa96a" font-size="8" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" letter-spacing="0.14em">NETWORK GUARD</text>
+  <!-- Analysis zone -->
+  <rect x="560" y="112" width="208" height="296" rx="8" fill="rgba(245,245,245,0.03)" stroke="rgba(245,245,245,0.12)" stroke-width="0.8"/>
+  <rect x="596" y="104" width="136" height="16" rx="2" fill="#22272e"/>
+  <text x="664" y="116" fill="rgba(245,245,245,0.45)" font-size="7" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" text-anchor="middle" letter-spacing="0.14em">ANALYSIS · INDEPENDENT</text>
+  <!-- Arrows, drawn before boxes -->
+  <line x1="184" y1="272" x2="216" y2="272" stroke="#bfc0c0" stroke-width="1.2" marker-end="url(#complydoc-architecture-dark-arrow)"/>
+  <line x1="352" y1="272" x2="384" y2="272" stroke="#bfc0c0" stroke-width="1.2" marker-end="url(#complydoc-architecture-dark-arrow)"/>
+  <path d="M 528,252 H 544 Q 552,252 552,244 V 184 Q 552,176 560,176 H 576" fill="none" stroke="#bfc0c0" stroke-width="1.2" marker-end="url(#complydoc-architecture-dark-arrow)"/>
+  <line x1="528" y1="272" x2="576" y2="272" stroke="#bfc0c0" stroke-width="1.2" marker-end="url(#complydoc-architecture-dark-arrow)"/>
+  <path d="M 528,292 H 544 Q 552,292 552,300 V 360 Q 552,368 560,368 H 576" fill="none" stroke="#bfc0c0" stroke-width="1.2" marker-end="url(#complydoc-architecture-dark-arrow)"/>
+  <line x1="664" y1="448" x2="664" y2="408" stroke="#bfc0c0" stroke-width="1.2" stroke-dasharray="4,3" marker-end="url(#complydoc-architecture-dark-arrow)"/>
+  <rect x="676" y="420" width="84" height="12" rx="2" fill="#22272e"/>
+  <text x="680" y="429" fill="#8e98ac" font-size="8" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" letter-spacing="0.06em">THRESHOLDS</text>
+  <line x1="768" y1="240" x2="804" y2="240" stroke="#bfc0c0" stroke-width="1.2" marker-end="url(#complydoc-architecture-dark-arrow)"/>
+  <path d="M 768,300 H 778 Q 786,300 786,308 V 328 Q 786,336 794,336 H 804" fill="none" stroke="#bfc0c0" stroke-width="1.2" marker-end="url(#complydoc-architecture-dark-arrow)"/>
+  <!-- Nodes -->
+  <rect x="48" y="240" width="136" height="64" rx="6" fill="#22272e"/>
+  <rect x="48" y="240" width="136" height="64" rx="6" fill="rgba(191,192,192,0.10)" stroke="#8e98ac" stroke-width="1"/>
+  <rect x="60" y="250" width="36" height="12" rx="2" fill="none" stroke="#8e98ac" stroke-opacity="0.40" stroke-width="0.8"/>
+  <text x="78.0" y="259" fill="#8e98ac" fill-opacity="0.85" font-size="7" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" text-anchor="middle" letter-spacing="0.08em">INPUT</text>
+  <text x="116.0" y="280.0" fill="#f5f5f5" font-size="12" font-weight="600" font-family="'Geist', 'Helvetica Neue', Helvetica, Arial, sans-serif" text-anchor="middle">documents/</text>
+  <text x="116.0" y="296.0" fill="#8e98ac" font-size="9" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" text-anchor="middle">pdf · img · docx · xlsx</text>
+  <rect x="216" y="240" width="136" height="64" rx="6" fill="#22272e"/>
+  <rect x="216" y="240" width="136" height="64" rx="6" fill="#2c323b" stroke="#f5f5f5" stroke-width="1"/>
+  <rect x="228" y="250" width="32" height="12" rx="2" fill="none" stroke="#f5f5f5" stroke-opacity="0.40" stroke-width="0.8"/>
+  <text x="244.0" y="259" fill="#f5f5f5" fill-opacity="0.85" font-size="7" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" text-anchor="middle" letter-spacing="0.08em">WALK</text>
+  <text x="284.0" y="280.0" fill="#f5f5f5" font-size="12" font-weight="600" font-family="'Geist', 'Helvetica Neue', Helvetica, Arial, sans-serif" text-anchor="middle">Discovery</text>
+  <text x="284.0" y="296.0" fill="#8e98ac" font-size="9" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" text-anchor="middle">skips unopenable</text>
+  <rect x="384" y="240" width="144" height="64" rx="6" fill="#22272e"/>
+  <rect x="384" y="240" width="144" height="64" rx="6" fill="#2c323b" stroke="#f5f5f5" stroke-width="1"/>
+  <rect x="396" y="250" width="32" height="12" rx="2" fill="none" stroke="#f5f5f5" stroke-opacity="0.40" stroke-width="0.8"/>
+  <text x="412.0" y="259" fill="#f5f5f5" fill-opacity="0.85" font-size="7" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" text-anchor="middle" letter-spacing="0.08em">LOAD</text>
+  <text x="456.0" y="280.0" fill="#f5f5f5" font-size="12" font-weight="600" font-family="'Geist', 'Helvetica Neue', Helvetica, Arial, sans-serif" text-anchor="middle">Ingest</text>
+  <text x="456.0" y="296.0" fill="#8e98ac" font-size="9" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" text-anchor="middle">per-format loaders</text>
+  <rect x="576" y="144" width="176" height="64" rx="6" fill="#22272e"/>
+  <rect x="576" y="144" width="176" height="64" rx="6" fill="#2c323b" stroke="#f5f5f5" stroke-width="1"/>
+  <rect x="588" y="154" width="20" height="12" rx="2" fill="none" stroke="#f5f5f5" stroke-opacity="0.40" stroke-width="0.8"/>
+  <text x="598.0" y="163" fill="#f5f5f5" fill-opacity="0.85" font-size="7" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" text-anchor="middle" letter-spacing="0.08em">01</text>
+  <text x="664.0" y="184.0" fill="#f5f5f5" font-size="12" font-weight="600" font-family="'Geist', 'Helvetica Neue', Helvetica, Arial, sans-serif" text-anchor="middle">Cost</text>
+  <text x="664.0" y="200.0" fill="#8e98ac" font-size="9" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" text-anchor="middle">tokens, pages, price</text>
+  <rect x="576" y="240" width="176" height="64" rx="6" fill="#22272e"/>
+  <rect x="576" y="240" width="176" height="64" rx="6" fill="#2c323b" stroke="#f5f5f5" stroke-width="1"/>
+  <rect x="588" y="250" width="20" height="12" rx="2" fill="none" stroke="#f5f5f5" stroke-opacity="0.40" stroke-width="0.8"/>
+  <text x="598.0" y="259" fill="#f5f5f5" fill-opacity="0.85" font-size="7" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" text-anchor="middle" letter-spacing="0.08em">02</text>
+  <text x="664.0" y="280.0" fill="#f5f5f5" font-size="12" font-weight="600" font-family="'Geist', 'Helvetica Neue', Helvetica, Arial, sans-serif" text-anchor="middle">Difficulty</text>
+  <text x="664.0" y="296.0" fill="#8e98ac" font-size="9" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" text-anchor="middle">18 measured signals</text>
+  <rect x="576" y="336" width="176" height="64" rx="6" fill="#22272e"/>
+  <rect x="576" y="336" width="176" height="64" rx="6" fill="rgba(47,169,106,0.14)" stroke="#2fa96a" stroke-width="1"/>
+  <rect x="588" y="346" width="20" height="12" rx="2" fill="none" stroke="#2fa96a" stroke-opacity="0.40" stroke-width="0.8"/>
+  <text x="598.0" y="355" fill="#2fa96a" fill-opacity="0.85" font-size="7" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" text-anchor="middle" letter-spacing="0.08em">03</text>
+  <text x="664.0" y="376.0" fill="#f5f5f5" font-size="12" font-weight="600" font-family="'Geist', 'Helvetica Neue', Helvetica, Arial, sans-serif" text-anchor="middle">Sensitive</text>
+  <text x="664.0" y="392.0" fill="#8e98ac" font-size="9" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" text-anchor="middle">masked by default</text>
+  <rect x="576" y="448" width="176" height="52" rx="6" fill="#22272e"/>
+  <rect x="576" y="448" width="176" height="52" rx="6" fill="rgba(245,245,245,0.06)" stroke="#bfc0c0" stroke-width="1"/>
+  <rect x="588" y="458" width="32" height="12" rx="2" fill="none" stroke="#bfc0c0" stroke-opacity="0.40" stroke-width="0.8"/>
+  <text x="604.0" y="467" fill="#bfc0c0" fill-opacity="0.85" font-size="7" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" text-anchor="middle" letter-spacing="0.08em">YAML</text>
+  <text x="664.0" y="482.0" fill="#f5f5f5" font-size="12" font-weight="600" font-family="'Geist', 'Helvetica Neue', Helvetica, Arial, sans-serif" text-anchor="middle">Config</text>
+  <text x="664.0" y="498.0" fill="#8e98ac" font-size="9" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" text-anchor="middle">prices · weights · patterns</text>
+  <rect x="804" y="208" width="136" height="64" rx="6" fill="#22272e"/>
+  <rect x="804" y="208" width="136" height="64" rx="6" fill="rgba(245,245,245,0.06)" stroke="#bfc0c0" stroke-width="1"/>
+  <rect x="816" y="218" width="32" height="12" rx="2" fill="none" stroke="#bfc0c0" stroke-opacity="0.40" stroke-width="0.8"/>
+  <text x="832.0" y="227" fill="#bfc0c0" fill-opacity="0.85" font-size="7" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" text-anchor="middle" letter-spacing="0.08em">JSON</text>
+  <text x="872.0" y="248.0" fill="#f5f5f5" font-size="12" font-weight="600" font-family="'Geist', 'Helvetica Neue', Helvetica, Arial, sans-serif" text-anchor="middle">report.json</text>
+  <text x="872.0" y="264.0" fill="#8e98ac" font-size="9" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" text-anchor="middle">machine readable</text>
+  <rect x="804" y="304" width="136" height="64" rx="6" fill="#22272e"/>
+  <rect x="804" y="304" width="136" height="64" rx="6" fill="rgba(245,245,245,0.06)" stroke="#bfc0c0" stroke-width="1"/>
+  <rect x="816" y="314" width="32" height="12" rx="2" fill="none" stroke="#bfc0c0" stroke-opacity="0.40" stroke-width="0.8"/>
+  <text x="832.0" y="323" fill="#bfc0c0" fill-opacity="0.85" font-size="7" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" text-anchor="middle" letter-spacing="0.08em">HTML</text>
+  <text x="872.0" y="344.0" fill="#f5f5f5" font-size="12" font-weight="600" font-family="'Geist', 'Helvetica Neue', Helvetica, Arial, sans-serif" text-anchor="middle">report.html</text>
+  <text x="872.0" y="360.0" fill="#8e98ac" font-size="9" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" text-anchor="middle">self-contained</text>
+  <!-- Legend -->
+  <line x1="24" y1="544" x2="976" y2="544" stroke="rgba(245,245,245,0.14)" stroke-width="0.8"/>
+  <text x="24" y="566" fill="#bfc0c0" font-size="8" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" letter-spacing="0.14em">LEGEND</text>
+  <rect x="112" y="556" width="14" height="12" rx="2" fill="rgba(47,169,106,0.14)" stroke="#2fa96a" stroke-width="1"/>
+  <text x="134" y="566" fill="#8e98ac" font-size="8" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace">MASKED VALUES</text>
+  <rect x="356" y="556" width="14" height="12" rx="2" fill="rgba(47,169,106,0.05)" stroke="rgba(47,169,106,0.60)" stroke-width="1" stroke-dasharray="3,3"/>
+  <text x="378" y="566" fill="#8e98ac" font-size="8" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace">NO OUTBOUND SOCKET</text>
+  <rect x="592" y="556" width="14" height="12" rx="2" fill="#2c323b" stroke="#f5f5f5" stroke-width="1"/>
+  <text x="614" y="566" fill="#8e98ac" font-size="8" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace">PIPELINE STAGE</text>
+  <rect x="792" y="556" width="14" height="12" rx="2" fill="rgba(245,245,245,0.06)" stroke="#bfc0c0" stroke-width="1"/>
+  <text x="814" y="566" fill="#8e98ac" font-size="8" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace">CONFIG AND OUTPUT</text>
+</svg>

complydoc-0.3.0/.github/images/complydoc-architecture.html ADDED Viewed

@@ -0,0 +1,148 @@
+<!doctype html>
+<html lang="en">
+<head>
+<meta charset="utf-8">
+<meta name="viewport" content="width=device-width, initial-scale=1">
+<title>complydoc — pipeline architecture</title>
+<link href="https://fonts.googleapis.com/css2?family=Instrument+Serif:ital@0;1&family=Geist:wght@400;500;600&family=Geist+Mono:wght@400;500;600&display=swap" rel="stylesheet">
+<style>
+  body { margin:0; background:#f5f5f5; color:#22272e;
+    font-family:'Geist',sans-serif; padding:3rem 2rem; }
+  .wrap { max-width:1080px; margin:0 auto; }
+  .eyebrow { font-family:'Geist Mono',monospace; font-size:8px; letter-spacing:0.14em;
+    text-transform:uppercase; color:#7a8399; margin:0 0 0.5rem; }
+  h1 { font-family:'Instrument Serif',serif; font-weight:400; font-size:1.75rem;
+    margin:0 0 0.25rem; }
+  .sub { color:#4f5d75; font-size:0.875rem; margin:0 0 2rem; max-width:64ch; }
+  svg { width:100%; height:auto; display:block; }
+</style>
+</head>
+<body>
+<div class="wrap">
+  <p class="eyebrow">complydoc</p>
+  <h1>Pipeline</h1>
+  <p class="sub">Files are read locally by per-format loaders, then passed to three analysis
+  components that run independently. Each run writes a JSON report and an HTML report.</p>
+  <svg viewBox="0 0 1000 600" role="img" aria-labelledby="complydoc-architecture-title complydoc-architecture-desc" xmlns="http://www.w3.org/2000/svg">
+  <title id="complydoc-architecture-title">complydoc pipeline architecture</title>
+  <desc id="complydoc-architecture-desc">A folder of documents passes through discovery and a format-specific ingest layer into three independent analysis components — cost, difficulty and sensitive data — which are driven by YAML config and emit a diffable JSON report and a self-contained HTML report. The whole pipeline sits inside a network guard boundary, so no document content can leave the machine.</desc>
+  <defs>
+    <marker id="complydoc-architecture-arrow" markerWidth="8" markerHeight="6" refX="7" refY="3" orient="auto">
+      <polygon points="0 0, 8 3, 0 6" fill="#4f5d75"/>
+    </marker>
+    <marker id="complydoc-architecture-arrow-accent" markerWidth="8" markerHeight="6" refX="7" refY="3" orient="auto">
+      <polygon points="0 0, 8 3, 0 6" fill="#1a7f4b"/>
+    </marker>
+  </defs>
+  <rect width="100%" height="100%" fill="#f5f5f5"/>
+  <!-- Network guard boundary: drawn first, behind everything -->
+  <rect x="24" y="72" width="940" height="440" rx="8" fill="rgba(26,127,75,0.04)" stroke="rgba(26,127,75,0.55)" stroke-width="1" stroke-dasharray="4,4"/>
+  <rect x="44" y="64" width="96" height="16" rx="2" fill="#f5f5f5"/>
+  <text x="52" y="76" fill="#1a7f4b" font-size="8" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" letter-spacing="0.14em">NETWORK GUARD</text>
+  <!-- Analysis zone -->
+  <rect x="560" y="112" width="208" height="296" rx="8" fill="rgba(34,39,46,0.02)" stroke="rgba(34,39,46,0.10)" stroke-width="0.8"/>
+  <rect x="596" y="104" width="136" height="16" rx="2" fill="#f5f5f5"/>
+  <text x="664" y="116" fill="rgba(34,39,46,0.40)" font-size="7" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" text-anchor="middle" letter-spacing="0.14em">ANALYSIS · INDEPENDENT</text>
+  <!-- Arrows, drawn before boxes -->
+  <line x1="184" y1="272" x2="216" y2="272" stroke="#4f5d75" stroke-width="1.2" marker-end="url(#complydoc-architecture-arrow)"/>
+  <line x1="352" y1="272" x2="384" y2="272" stroke="#4f5d75" stroke-width="1.2" marker-end="url(#complydoc-architecture-arrow)"/>
+  <path d="M 528,252 H 544 Q 552,252 552,244 V 184 Q 552,176 560,176 H 576" fill="none" stroke="#4f5d75" stroke-width="1.2" marker-end="url(#complydoc-architecture-arrow)"/>
+  <line x1="528" y1="272" x2="576" y2="272" stroke="#4f5d75" stroke-width="1.2" marker-end="url(#complydoc-architecture-arrow)"/>
+  <path d="M 528,292 H 544 Q 552,292 552,300 V 360 Q 552,368 560,368 H 576" fill="none" stroke="#4f5d75" stroke-width="1.2" marker-end="url(#complydoc-architecture-arrow)"/>
+  <line x1="664" y1="448" x2="664" y2="408" stroke="#4f5d75" stroke-width="1.2" stroke-dasharray="4,3" marker-end="url(#complydoc-architecture-arrow)"/>
+  <rect x="676" y="420" width="84" height="12" rx="2" fill="#f5f5f5"/>
+  <text x="680" y="429" fill="#7a8399" font-size="8" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" letter-spacing="0.06em">THRESHOLDS</text>
+  <line x1="768" y1="240" x2="804" y2="240" stroke="#4f5d75" stroke-width="1.2" marker-end="url(#complydoc-architecture-arrow)"/>
+  <path d="M 768,300 H 778 Q 786,300 786,308 V 328 Q 786,336 794,336 H 804" fill="none" stroke="#4f5d75" stroke-width="1.2" marker-end="url(#complydoc-architecture-arrow)"/>
+  <!-- Nodes -->
+  <rect x="48" y="240" width="136" height="64" rx="6" fill="#f5f5f5"/>
+  <rect x="48" y="240" width="136" height="64" rx="6" fill="rgba(79,93,117,0.10)" stroke="#7a8399" stroke-width="1"/>
+  <rect x="60" y="250" width="36" height="12" rx="2" fill="none" stroke="#7a8399" stroke-opacity="0.40" stroke-width="0.8"/>
+  <text x="78.0" y="259" fill="#7a8399" fill-opacity="0.85" font-size="7" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" text-anchor="middle" letter-spacing="0.08em">INPUT</text>
+  <text x="116.0" y="280.0" fill="#22272e" font-size="12" font-weight="600" font-family="'Geist', 'Helvetica Neue', Helvetica, Arial, sans-serif" text-anchor="middle">documents/</text>
+  <text x="116.0" y="296.0" fill="#7a8399" font-size="9" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" text-anchor="middle">pdf · img · docx · xlsx</text>
+  <rect x="216" y="240" width="136" height="64" rx="6" fill="#f5f5f5"/>
+  <rect x="216" y="240" width="136" height="64" rx="6" fill="#ffffff" stroke="#22272e" stroke-width="1"/>
+  <rect x="228" y="250" width="32" height="12" rx="2" fill="none" stroke="#22272e" stroke-opacity="0.40" stroke-width="0.8"/>
+  <text x="244.0" y="259" fill="#22272e" fill-opacity="0.85" font-size="7" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" text-anchor="middle" letter-spacing="0.08em">WALK</text>
+  <text x="284.0" y="280.0" fill="#22272e" font-size="12" font-weight="600" font-family="'Geist', 'Helvetica Neue', Helvetica, Arial, sans-serif" text-anchor="middle">Discovery</text>
+  <text x="284.0" y="296.0" fill="#7a8399" font-size="9" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" text-anchor="middle">skips unopenable</text>
+  <rect x="384" y="240" width="144" height="64" rx="6" fill="#f5f5f5"/>
+  <rect x="384" y="240" width="144" height="64" rx="6" fill="#ffffff" stroke="#22272e" stroke-width="1"/>
+  <rect x="396" y="250" width="32" height="12" rx="2" fill="none" stroke="#22272e" stroke-opacity="0.40" stroke-width="0.8"/>
+  <text x="412.0" y="259" fill="#22272e" fill-opacity="0.85" font-size="7" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" text-anchor="middle" letter-spacing="0.08em">LOAD</text>
+  <text x="456.0" y="280.0" fill="#22272e" font-size="12" font-weight="600" font-family="'Geist', 'Helvetica Neue', Helvetica, Arial, sans-serif" text-anchor="middle">Ingest</text>
+  <text x="456.0" y="296.0" fill="#7a8399" font-size="9" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" text-anchor="middle">per-format loaders</text>
+  <rect x="576" y="144" width="176" height="64" rx="6" fill="#f5f5f5"/>
+  <rect x="576" y="144" width="176" height="64" rx="6" fill="#ffffff" stroke="#22272e" stroke-width="1"/>
+  <rect x="588" y="154" width="20" height="12" rx="2" fill="none" stroke="#22272e" stroke-opacity="0.40" stroke-width="0.8"/>
+  <text x="598.0" y="163" fill="#22272e" fill-opacity="0.85" font-size="7" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" text-anchor="middle" letter-spacing="0.08em">01</text>
+  <text x="664.0" y="184.0" fill="#22272e" font-size="12" font-weight="600" font-family="'Geist', 'Helvetica Neue', Helvetica, Arial, sans-serif" text-anchor="middle">Cost</text>
+  <text x="664.0" y="200.0" fill="#7a8399" font-size="9" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" text-anchor="middle">tokens, pages, price</text>
+  <rect x="576" y="240" width="176" height="64" rx="6" fill="#f5f5f5"/>
+  <rect x="576" y="240" width="176" height="64" rx="6" fill="#ffffff" stroke="#22272e" stroke-width="1"/>
+  <rect x="588" y="250" width="20" height="12" rx="2" fill="none" stroke="#22272e" stroke-opacity="0.40" stroke-width="0.8"/>
+  <text x="598.0" y="259" fill="#22272e" fill-opacity="0.85" font-size="7" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" text-anchor="middle" letter-spacing="0.08em">02</text>
+  <text x="664.0" y="280.0" fill="#22272e" font-size="12" font-weight="600" font-family="'Geist', 'Helvetica Neue', Helvetica, Arial, sans-serif" text-anchor="middle">Difficulty</text>
+  <text x="664.0" y="296.0" fill="#7a8399" font-size="9" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" text-anchor="middle">18 measured signals</text>
+  <rect x="576" y="336" width="176" height="64" rx="6" fill="#f5f5f5"/>
+  <rect x="576" y="336" width="176" height="64" rx="6" fill="rgba(26,127,75,0.08)" stroke="#1a7f4b" stroke-width="1"/>
+  <rect x="588" y="346" width="20" height="12" rx="2" fill="none" stroke="#1a7f4b" stroke-opacity="0.40" stroke-width="0.8"/>
+  <text x="598.0" y="355" fill="#1a7f4b" fill-opacity="0.85" font-size="7" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" text-anchor="middle" letter-spacing="0.08em">03</text>
+  <text x="664.0" y="376.0" fill="#22272e" font-size="12" font-weight="600" font-family="'Geist', 'Helvetica Neue', Helvetica, Arial, sans-serif" text-anchor="middle">Sensitive</text>
+  <text x="664.0" y="392.0" fill="#7a8399" font-size="9" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" text-anchor="middle">masked by default</text>
+  <rect x="576" y="448" width="176" height="52" rx="6" fill="#f5f5f5"/>
+  <rect x="576" y="448" width="176" height="52" rx="6" fill="rgba(34,39,46,0.05)" stroke="#4f5d75" stroke-width="1"/>
+  <rect x="588" y="458" width="32" height="12" rx="2" fill="none" stroke="#4f5d75" stroke-opacity="0.40" stroke-width="0.8"/>
+  <text x="604.0" y="467" fill="#4f5d75" fill-opacity="0.85" font-size="7" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" text-anchor="middle" letter-spacing="0.08em">YAML</text>
+  <text x="664.0" y="482.0" fill="#22272e" font-size="12" font-weight="600" font-family="'Geist', 'Helvetica Neue', Helvetica, Arial, sans-serif" text-anchor="middle">Config</text>
+  <text x="664.0" y="498.0" fill="#7a8399" font-size="9" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" text-anchor="middle">prices · weights · patterns</text>
+  <rect x="804" y="208" width="136" height="64" rx="6" fill="#f5f5f5"/>
+  <rect x="804" y="208" width="136" height="64" rx="6" fill="rgba(34,39,46,0.05)" stroke="#4f5d75" stroke-width="1"/>
+  <rect x="816" y="218" width="32" height="12" rx="2" fill="none" stroke="#4f5d75" stroke-opacity="0.40" stroke-width="0.8"/>
+  <text x="832.0" y="227" fill="#4f5d75" fill-opacity="0.85" font-size="7" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" text-anchor="middle" letter-spacing="0.08em">JSON</text>
+  <text x="872.0" y="248.0" fill="#22272e" font-size="12" font-weight="600" font-family="'Geist', 'Helvetica Neue', Helvetica, Arial, sans-serif" text-anchor="middle">report.json</text>
+  <text x="872.0" y="264.0" fill="#7a8399" font-size="9" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" text-anchor="middle">machine readable</text>
+  <rect x="804" y="304" width="136" height="64" rx="6" fill="#f5f5f5"/>
+  <rect x="804" y="304" width="136" height="64" rx="6" fill="rgba(34,39,46,0.05)" stroke="#4f5d75" stroke-width="1"/>
+  <rect x="816" y="314" width="32" height="12" rx="2" fill="none" stroke="#4f5d75" stroke-opacity="0.40" stroke-width="0.8"/>
+  <text x="832.0" y="323" fill="#4f5d75" fill-opacity="0.85" font-size="7" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" text-anchor="middle" letter-spacing="0.08em">HTML</text>
+  <text x="872.0" y="344.0" fill="#22272e" font-size="12" font-weight="600" font-family="'Geist', 'Helvetica Neue', Helvetica, Arial, sans-serif" text-anchor="middle">report.html</text>
+  <text x="872.0" y="360.0" fill="#7a8399" font-size="9" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" text-anchor="middle">self-contained</text>
+  <!-- Legend -->
+  <line x1="24" y1="544" x2="976" y2="544" stroke="rgba(34,39,46,0.12)" stroke-width="0.8"/>
+  <text x="24" y="566" fill="#4f5d75" font-size="8" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace" letter-spacing="0.14em">LEGEND</text>
+  <rect x="112" y="556" width="14" height="12" rx="2" fill="rgba(26,127,75,0.08)" stroke="#1a7f4b" stroke-width="1"/>
+  <text x="134" y="566" fill="#7a8399" font-size="8" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace">MASKED VALUES</text>
+  <rect x="356" y="556" width="14" height="12" rx="2" fill="rgba(26,127,75,0.04)" stroke="rgba(26,127,75,0.55)" stroke-width="1" stroke-dasharray="3,3"/>
+  <text x="378" y="566" fill="#7a8399" font-size="8" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace">NO OUTBOUND SOCKET</text>
+  <rect x="592" y="556" width="14" height="12" rx="2" fill="#ffffff" stroke="#22272e" stroke-width="1"/>
+  <text x="614" y="566" fill="#7a8399" font-size="8" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace">PIPELINE STAGE</text>
+  <rect x="792" y="556" width="14" height="12" rx="2" fill="rgba(34,39,46,0.05)" stroke="#4f5d75" stroke-width="1"/>
+  <text x="814" y="566" fill="#7a8399" font-size="8" font-family="'Geist Mono', ui-monospace, 'SF Mono', Menlo, Consolas, monospace">CONFIG AND OUTPUT</text>
+</svg>
+</div>
+</body>
+</html>