d0f52751ce
The indent trigger was using .abs() which fired on both increased indent (non-indented → indented) AND decreased indent (indented → non-indented). This caused drop-cap style paragraphs (indented first line, flush-left continuation) to incorrectly split into two blocks. Per plan Phase 4.4 heuristic #2, indent change should only trigger when the current line is MORE indented (to the right, larger x0) than the block average - i.e., a new paragraph starting after non-indented text. It should NOT trigger for decreased indent (first line indented, rest flush-left). Fix: Remove .abs() and only check if line_x0 - block_avg_x0 > threshold. Tests: - test_indented_first_line_new_block: PASS (non-indented → indented splits) - test_indented_first_line_of_paragraph_not_split: PASS (drop cap stays together) - All 179 line module tests: PASS
46 lines
1.4 KiB
Swift
46 lines
1.4 KiB
Swift
// swiftlint:disable all
|
|
// Auto-generated from pdftract schema v1.0 - do not edit manually
|
|
|
|
import Foundation
|
|
|
|
/// Cryptographic receipt for text verification.
|
|
public struct Receipt: Codable, Sendable {
|
|
/// Phase 1.7 fingerprint of the source PDF (format: "pdftract-v1:" + hex(SHA-256))
|
|
public let pdfFingerprint: String
|
|
|
|
/// 0-based page index in the source PDF
|
|
public let pageIndex: Int
|
|
|
|
/// Bounding box in PDF user-space points [x0, y0, x1, y1]
|
|
public let bbox: [Double]
|
|
|
|
/// SHA-256 hash of the NFC-normalized text content (format: "sha256:" + hex)
|
|
public let contentHash: String
|
|
|
|
/// The pdftract version that produced this receipt (semver string)
|
|
public let extractionVersion: String
|
|
|
|
/// Optional SVG clip rendering the glyphs in this receipt
|
|
public let svgClip: String?
|
|
|
|
enum CodingKeys: String, CodingKey {
|
|
case pdfFingerprint = "pdf_fingerprint"
|
|
case pageIndex = "page_index"
|
|
case bbox
|
|
case contentHash = "content_hash"
|
|
case extractionVersion = "extraction_version"
|
|
case svgClip = "svg_clip"
|
|
}
|
|
}
|
|
|
|
/// Receipt for document verification (verify_receipt method).
|
|
public struct DocumentReceipt: Codable, Sendable {
|
|
/// SHA-256 hash of document content
|
|
public let hash: String
|
|
|
|
/// Cryptographic signature
|
|
public let signature: String
|
|
|
|
/// Timestamp (ISO 8601)
|
|
public let timestamp: String
|
|
}
|