@laitszkin/apollo-toolkit 3.13.2 → 3.14.0

package/weekly-financial-event-report/scripts/extract_pdf_text_pdfkit.swift

@@ -1,99 +0,0 @@
-#!/usr/bin/env swift
-
-import Foundation
-import PDFKit
-
-let helpText = """
-apltk extract-pdf-text-pdfkit — extract PDF text with macOS PDFKit.
-
-Usage:
-  apltk extract-pdf-text-pdfkit /absolute/path/to/source.pdf
-  swift weekly-financial-event-report/scripts/extract_pdf_text_pdfkit.swift /absolute/path/to/source.pdf
-
-Use this when:
-  - You need a simple macOS PDFKit-based text extraction fallback.
-
-Examples:
-  apltk extract-pdf-text-pdfkit /absolute/path/to/source.pdf
-    Result: prints `PDF_PATH=...`, `PAGE_COUNT=...`, and one `=== PAGE N ===` section per extracted page.
-"""
-
-struct Arguments {
-    let pdfPath: String
-}
-
-enum ExtractionError: Error, CustomStringConvertible {
-    case missingPath
-    case unsupportedPlatform
-    case unreadablePDF(String)
-
-    var description: String {
-        switch self {
-        case .missingPath:
-            return "Usage: swift scripts/extract_pdf_text_pdfkit.swift /absolute/path/to/source.pdf\nRun with --help for the full command guide."
-        case .unsupportedPlatform:
-            return "PDFKit extraction is only supported on macOS."
-        case .unreadablePDF(let path):
-            return "Unable to open PDF at \(path)"
-        }
-    }
-}
-
-enum ParseResult {
-    case help
-    case arguments(Arguments)
-}
-
-func parseArguments() throws -> ParseResult {
-    let args = Array(CommandLine.arguments.dropFirst())
-    if args.contains("--help") || args.contains("-h") {
-        return .help
-    }
-    guard let pdfPath = args.first, !pdfPath.isEmpty else {
-        throw ExtractionError.missingPath
-    }
-    return .arguments(Arguments(pdfPath: pdfPath))
-}
-
-func main() throws {
-    #if !os(macOS)
-    throw ExtractionError.unsupportedPlatform
-    #else
-    switch try parseArguments() {
-    case .help:
-        print(helpText)
-        return
-    case .arguments(let arguments):
-    let pdfURL = URL(fileURLWithPath: arguments.pdfPath)
-
-    guard let document = PDFDocument(url: pdfURL) else {
-        throw ExtractionError.unreadablePDF(arguments.pdfPath)
-    }
-
-    print("PDF_PATH=\(arguments.pdfPath)")
-    print("PAGE_COUNT=\(document.pageCount)")
-
-    for pageIndex in 0..<document.pageCount {
-        guard let page = document.page(at: pageIndex) else {
-            continue
-        }
-        let text = page.string?
-            .replacingOccurrences(of: "\u{000C}", with: "\n")
-            .trimmingCharacters(in: .whitespacesAndNewlines) ?? ""
-        print("=== PAGE \(pageIndex + 1) ===")
-        if text.isEmpty {
-            print("[NO_TEXT_EXTRACTED]")
-        } else {
-            print(text)
-        }
-    }
-    }
-    #endif
-}
-
-do {
-    try main()
-} catch {
-    fputs("\(error)\n", stderr)
-    exit(1)
-}

package/weekly-financial-event-report/tests/test_extract_pdf_text_pdfkit.py

@@ -1,64 +0,0 @@
-#!/usr/bin/env python3
-
-from __future__ import annotations
-
-import importlib.util
-import shutil
-import subprocess
-import sys
-import tempfile
-import unittest
-from pathlib import Path
-
-REPORTLAB_AVAILABLE = importlib.util.find_spec("reportlab") is not None
-
-if REPORTLAB_AVAILABLE:
-    from reportlab.pdfgen import canvas
-
-
-SCRIPT_PATH = Path(__file__).resolve().parents[1] / "scripts" / "extract_pdf_text_pdfkit.swift"
-
-
-@unittest.skipUnless(shutil.which("swift"), "swift is required for PDFKit script tests")
-@unittest.skipUnless(sys.platform == "darwin", "PDFKit script tests only work on macOS")
-class ExtractPdfTextPdfkitTests(unittest.TestCase):
-    def run_script(self, *args: str) -> subprocess.CompletedProcess[str]:
-        return subprocess.run(
-            ["swift", str(SCRIPT_PATH), *args],
-            capture_output=True,
-            text=True,
-            check=False,
-        )
-
-    def test_missing_path_prints_usage(self) -> None:
-        result = self.run_script()
-        self.assertEqual(result.returncode, 1)
-        self.assertIn("Usage: swift scripts/extract_pdf_text_pdfkit.swift", result.stderr)
-
-    def test_unreadable_pdf_reports_missing_file(self) -> None:
-        result = self.run_script("/tmp/does-not-exist.pdf")
-        self.assertEqual(result.returncode, 1)
-        self.assertIn("Unable to open PDF", result.stderr)
-
-    @unittest.skipUnless(REPORTLAB_AVAILABLE, "reportlab is required to generate fixture PDFs")
-    def test_extracts_text_from_generated_pdf(self) -> None:
-        with tempfile.TemporaryDirectory() as temp_dir:
-            pdf_path = Path(temp_dir) / "sample.pdf"
-            pdf = canvas.Canvas(str(pdf_path))
-            pdf.drawString(72, 720, "Weekly event headline")
-            pdf.showPage()
-            pdf.drawString(72, 720, "Second page details")
-            pdf.save()
-
-            result = self.run_script(str(pdf_path))
-
-        self.assertEqual(result.returncode, 0, result.stderr)
-        self.assertIn(f"PDF_PATH={pdf_path}", result.stdout)
-        self.assertIn("PAGE_COUNT=2", result.stdout)
-        self.assertIn("=== PAGE 1 ===", result.stdout)
-        self.assertIn("Weekly event headline", result.stdout)
-        self.assertIn("Second page details", result.stdout)
-
-
-if __name__ == "__main__":
-    unittest.main()