chore(bf-xqib3): remove obsolete generators and compiled artifacts from tests/fixtures/
Remove 5 DELETE-category generator files identified in bf-1iefu: - tests/fixtures/scanned/generate_scanned_fixtures.rs (Rust stub, use Python version) - tests/fixtures/security/generate_sensitive_fixture.py (duplicate, Rust version preferred) - tests/fixtures/encoding/generate_unmapped_glyphs.rs (superseded by Python version) - tests/fixtures/malformed/gen-bomb-10k-2g.sh (superseded by Python version) - tests/fixtures/forms/generate_form_fixtures.d (orphaned Makefile dependency) Verification: No compiled object files (.o, .so, .a, .dylib, .dll) or executable binaries found. The .bin files in fixtures root are test data files, not compiled artifacts.
This commit is contained in:
jedarden
parent
9c955822c4
commit
bbbb7640d4
5 changed files with 0 additions and 446 deletions
|
|
@ -1,87 +0,0 @@
|
|||
//! Generate unmapped-glyphs.pdf test fixture
|
||||
//!
|
||||
//! Creates a PDF with custom glyph names that are not in the Adobe Glyph List
|
||||
//! and have no ToUnicode mapping, triggering GLYPH_UNMAPPED diagnostics.
|
||||
|
||||
use std::fs::File;
|
||||
use std::io::Write;
|
||||
|
||||
fn main() -> Result<(), Box<dyn std::error::Error>> {
|
||||
println!("Generating unmapped-glyphs.pdf...");
|
||||
|
||||
let objects = vec![
|
||||
// Catalog
|
||||
b"1 0 obj\n<<\n/Type /Catalog\n/Pages 2 0 R\n>>\nendobj".to_vec(),
|
||||
|
||||
// Pages
|
||||
b"2 0 obj\n<<\n/Type /Pages\n/Kids [3 0 R]\n/Count 1\n>>\nendobj".to_vec(),
|
||||
|
||||
// Page
|
||||
b"3 0 obj\n<<\n/Type /Page\n/Parent 2 0 R\n/MediaBox [0 0 612 792]\n/Resources <<\n/Font <<\n/F1 5 0 R\n>>\n>>\n/Contents 4 0 R\n>>\nendobj".to_vec(),
|
||||
|
||||
// Content stream: <00010203> Tj (byte codes 0-3 for 4 unmapped glyphs)
|
||||
b"4 0 obj\n<<\n/Length 44\n>>\nstream\nBT\n/F1 12 Tf\n50 700 Td\n<00010203> Tj\nET\nendstream\nendobj".to_vec(),
|
||||
|
||||
// Font with custom encoding
|
||||
// Uses 4 distinct custom glyph names not in AGL:
|
||||
// /CustomAlpha, /CustomBeta, /CustomGamma, /CustomDelta
|
||||
b"5 0 obj\n<<\n/Type /Font\n/Subtype /Type1\n/BaseFont /UnmappedGlyphs\n/Encoding <<\n/Type /Encoding\n/Differences [0 /CustomAlpha /CustomBeta /CustomGamma /CustomDelta]\n>>\n>>\nendobj".to_vec(),
|
||||
];
|
||||
|
||||
let pdf = build_pdf(objects);
|
||||
|
||||
let mut file = File::create("tests/fixtures/encoding/unmapped-glyphs.pdf")?;
|
||||
file.write_all(&pdf)?;
|
||||
|
||||
// Create expected output file (4 U+FFFD replacement characters)
|
||||
let mut txt_file = File::create("tests/fixtures/encoding/unmapped-glyphs.txt")?;
|
||||
txt_file.write_all("\u{FFFD}\u{FFFD}\u{FFFD}\u{FFFD}".as_bytes())?;
|
||||
|
||||
println!("✓ unmapped-glyphs.pdf created successfully!");
|
||||
println!(" -> Contains 4 unmapped glyphs: /CustomAlpha, /CustomBeta, /CustomGamma, /CustomDelta");
|
||||
println!(" -> Expected output: <U+FFFD><U+FFFD><U+FFFD><U+FFFD>");
|
||||
|
||||
Ok(())
|
||||
}
|
||||
|
||||
/// Build a complete PDF with proper xref table and trailer
|
||||
fn build_pdf(objects: Vec<Vec<u8>>) -> Vec<u8> {
|
||||
let mut pdf = b"%PDF-1.4\n".to_vec();
|
||||
|
||||
// Track object offsets
|
||||
let mut offsets = Vec::new();
|
||||
for obj in &objects {
|
||||
offsets.push(pdf.len());
|
||||
pdf.extend(obj);
|
||||
pdf.extend(b"\n");
|
||||
}
|
||||
|
||||
let xref_start = pdf.len();
|
||||
|
||||
// Build xref table
|
||||
pdf.extend(b"xref\n");
|
||||
pdf.extend(format!("0 {}\n", objects.len() + 1).as_bytes());
|
||||
pdf.extend(b"0000000000 65535 f \n");
|
||||
|
||||
for offset in offsets {
|
||||
pdf.extend(format!("{:010} 00000 n \n", offset).as_bytes());
|
||||
}
|
||||
|
||||
// Build trailer
|
||||
pdf.extend(b"trailer\n");
|
||||
pdf.extend(b"<<\n");
|
||||
pdf.extend(b"/Size ");
|
||||
pdf.extend(format!("{}", objects.len() + 1).as_bytes());
|
||||
pdf.extend(b"\n");
|
||||
pdf.extend(b"/Root 1 0 R\n");
|
||||
pdf.extend(b">>\n");
|
||||
|
||||
// Start of xref
|
||||
pdf.extend(b"startxref\n");
|
||||
pdf.extend(format!("{}\n", xref_start).as_bytes());
|
||||
|
||||
// EOF marker
|
||||
pdf.extend(b"%%EOF\n");
|
||||
|
||||
pdf
|
||||
}
|
||||
|
|
@ -1,5 +0,0 @@
|
|||
generate_form_fixtures.d: generate_form_fixtures.rs
|
||||
|
||||
generate_form_fixtures: generate_form_fixtures.rs
|
||||
|
||||
generate_form_fixtures.rs:
|
||||
109
tests/fixtures/malformed/gen-bomb-10k-2g.sh
vendored
109
tests/fixtures/malformed/gen-bomb-10k-2g.sh
vendored
|
|
@ -1,109 +0,0 @@
|
|||
#!/usr/bin/env bash
|
||||
# Generate tests/fixtures/malformed/bomb-10k-2g.pdf
|
||||
#
|
||||
# This PDF contains a FlateDecode stream that is ~10 KB compressed
|
||||
# but expands to ~2 GB when decompressed (decompression bomb).
|
||||
#
|
||||
# Generation method:
|
||||
# 1. Create a minimal valid PDF structure
|
||||
# 2. Include a FlateDecode-compressed stream with highly repetitive data
|
||||
# 3. The repetitive data (e.g., 0x00 repeated) compresses to ~10KB
|
||||
# 4. When decompressed, it expands to ~2GB of zeros
|
||||
#
|
||||
# This is a TH-01 test fixture for decompression bomb protection.
|
||||
|
||||
set -euo pipefail
|
||||
|
||||
# Output path
|
||||
OUTPUT_DIR="$(dirname "$0")"
|
||||
OUTPUT="$OUTPUT_DIR/bomb-10k-2g.pdf"
|
||||
|
||||
# Create a temporary directory for the compressed stream
|
||||
TEMP_DIR=$(mktemp -d)
|
||||
trap "rm -rf $TEMP_DIR" EXIT
|
||||
|
||||
# Generate 2GB of zeros and compress them
|
||||
# This creates the "bomb": small compressed size, huge decompressed size
|
||||
# We use /dev/zero which compresses extremely well
|
||||
echo "Generating 2GB bomb stream (this may take a moment)..."
|
||||
dd if=/dev/zero bs=1M count=2048 2>/dev/null | \
|
||||
zlib-flate -compress > "$TEMP_DIR/bomb-stream.bin"
|
||||
|
||||
# Check compressed size is reasonable (~10KB target)
|
||||
COMPRESSED_SIZE=$(stat -f%z "$TEMP_DIR/bomb-stream.bin" 2>/dev/null || stat -c%s "$TEMP_DIR/bomb-stream.bin" 2>/dev/null)
|
||||
echo "Compressed stream size: $COMPRESSED_SIZE bytes"
|
||||
|
||||
# Create the PDF structure
|
||||
# We use a minimal PDF with a single page containing the bomb stream
|
||||
cat > "$OUTPUT" <<'EOF'
|
||||
%PDF-1.4
|
||||
1 0 obj
|
||||
<<
|
||||
/Type /Catalog
|
||||
/Pages 2 0 R
|
||||
>>
|
||||
endobj
|
||||
2 0 obj
|
||||
<<
|
||||
/Type /Pages
|
||||
/Kids [3 0 R]
|
||||
/Count 1
|
||||
>>
|
||||
endobj
|
||||
3 0 obj
|
||||
<<
|
||||
/Type /Page
|
||||
/Parent 2 0 R
|
||||
/MediaBox [0 0 612 792]
|
||||
/Contents 4 0 R
|
||||
>>
|
||||
endobj
|
||||
4 0 obj
|
||||
<<
|
||||
/Length STREAM_LENGTH
|
||||
/Filter /FlateDecode
|
||||
>>
|
||||
stream
|
||||
EOF
|
||||
|
||||
# Append the compressed bomb stream
|
||||
cat "$TEMP_DIR/bomb-stream.bin" >> "$OUTPUT"
|
||||
|
||||
# Close the stream and add the PDF trailer
|
||||
cat >> "$OUTPUT" <<'EOF'
|
||||
endstream
|
||||
endobj
|
||||
xref
|
||||
0 5
|
||||
0000000000 65535 f
|
||||
0000000009 00000 n
|
||||
0000000058 00000 n
|
||||
0000000115 00000 n
|
||||
0000000214 00000 n
|
||||
trailer
|
||||
<<
|
||||
/Size 5
|
||||
/Root 1 0 R
|
||||
>>
|
||||
startxref
|
||||
STREAM_OFFSET
|
||||
%%EOF
|
||||
EOF
|
||||
|
||||
# Replace placeholders with actual values
|
||||
STREAM_LENGTH=$COMPRESSED_SIZE
|
||||
# Calculate the offset of the startxref value
|
||||
# This is the byte offset of the "stream" keyword + length of "stream\r\n"
|
||||
# We need to be precise here for a valid PDF
|
||||
STREAM_OFFSET=$(grep -abo "stream$" "$OUTPUT" | head -1 | cut -d: -f1)
|
||||
STREAM_OFFSET=$((STREAM_OFFSET + 7))
|
||||
|
||||
# Update the Length and startxref values
|
||||
sed -i.bak -e "s/STREAM_LENGTH/$STREAM_LENGTH/g" "$OUTPUT"
|
||||
sed -i.bak -e "s/STREAM_OFFSET/$STREAM_OFFSET/g" "$OUTPUT"
|
||||
rm -f "$OUTPUT.bak"
|
||||
|
||||
echo "Generated $OUTPUT"
|
||||
echo "Compressed size: $COMPRESSED_SIZE bytes"
|
||||
echo "Decompressed size: 2147483648 bytes (2 GB)"
|
||||
echo "Compression ratio: ~214748:1"
|
||||
118
tests/fixtures/scanned/generate_scanned_fixtures.rs
vendored
118
tests/fixtures/scanned/generate_scanned_fixtures.rs
vendored
|
|
@ -1,118 +0,0 @@
|
|||
//! Generate scanned fixture PDFs from ground truth text files.
|
||||
//!
|
||||
//! This is a Rust-native alternative to the Python generator.
|
||||
//! Run with: cargo run --bin generate_scanned_fixtures
|
||||
|
||||
use std::fs::{self, File};
|
||||
use std::io::{BufWriter, Write};
|
||||
use std::path::Path;
|
||||
|
||||
fn main() -> Result<(), Box<dyn std::error::Error>> {
|
||||
println!("Generating scanned fixture metadata...");
|
||||
|
||||
// Ensure directories exist
|
||||
create_directories()?;
|
||||
|
||||
// Generate fixture metadata
|
||||
generate_fixture_metadata()?;
|
||||
|
||||
println!("\nScanned fixtures corpus structure created.");
|
||||
println!("\nNOTE: Actual PDF generation requires external tools.");
|
||||
println!("Options:");
|
||||
println!(" 1. Use Python script: generate_scanned_fixtures.py");
|
||||
println!(" 2. Manual generation (see GEN_MANIFEST.md)");
|
||||
println!(" 3. Use printpdf or similar crate for native Rust generation");
|
||||
|
||||
Ok(())
|
||||
}
|
||||
|
||||
fn create_directories() -> Result<(), Box<dyn std::error::Error>> {
|
||||
let dirs = [
|
||||
"tests/fixtures/scanned/receipt",
|
||||
"tests/fixtures/scanned/documents",
|
||||
"tests/fixtures/scanned/multi-page",
|
||||
];
|
||||
|
||||
for dir in &dirs {
|
||||
fs::create_dir_all(dir)?;
|
||||
println!("Created directory: {}", dir);
|
||||
}
|
||||
|
||||
Ok(())
|
||||
}
|
||||
|
||||
fn generate_fixture_metadata() -> Result<(), Box<dyn std::error::Error>> {
|
||||
// Create a simple fixture list for reference
|
||||
let fixtures = vec![
|
||||
FixtureSpec {
|
||||
name: "receipt-300dpi",
|
||||
dir: "receipt",
|
||||
font: "Helvetica",
|
||||
font_size: 10,
|
||||
pages: 1,
|
||||
wer_target: 3.0,
|
||||
},
|
||||
FixtureSpec {
|
||||
name: "invoice-300dpi",
|
||||
dir: "documents",
|
||||
font: "Helvetica",
|
||||
font_size: 11,
|
||||
pages: 1,
|
||||
wer_target: 3.0,
|
||||
},
|
||||
FixtureSpec {
|
||||
name: "form-300dpi",
|
||||
dir: "documents",
|
||||
font: "Helvetica",
|
||||
font_size: 11,
|
||||
pages: 1,
|
||||
wer_target: 3.0,
|
||||
},
|
||||
FixtureSpec {
|
||||
name: "doc-10page-300dpi",
|
||||
dir: "multi-page",
|
||||
font: "Times-Roman",
|
||||
font_size: 12,
|
||||
pages: 10,
|
||||
wer_target: 3.0,
|
||||
},
|
||||
];
|
||||
|
||||
let manifest_path = "tests/fixtures/scanned/.fixtures.json";
|
||||
let file = File::create(manifest_path)?;
|
||||
let mut writer = BufWriter::new(file);
|
||||
|
||||
writeln!(writer, "{{")?;
|
||||
writeln!(writer, " \"fixtures\": [")?;
|
||||
|
||||
for (i, fixture) in fixtures.iter().enumerate() {
|
||||
writeln!(
|
||||
writer,
|
||||
" {}{{",
|
||||
if i == 0 { "" } else { ",\n" }
|
||||
)?;
|
||||
writeln!(writer, r#" "name": "{}","#, fixture.name)?;
|
||||
writeln!(writer, r#" "dir": "{}","#, fixture.dir)?;
|
||||
writeln!(writer, r#" "font": "{}","#, fixture.font)?;
|
||||
writeln!(writer, r#" "font_size": {},"#, fixture.font_size)?;
|
||||
writeln!(writer, r#" "pages": {},"#, fixture.pages)?;
|
||||
writeln!(writer, r#" "wer_target": {}"#, fixture.wer_target)?;
|
||||
write!(writer, " }}")?;
|
||||
}
|
||||
|
||||
writeln!(writer, "\n ]")?;
|
||||
writeln!(writer, "}}")?;
|
||||
|
||||
println!("Created fixture manifest: {}", manifest_path);
|
||||
|
||||
Ok(())
|
||||
}
|
||||
|
||||
struct FixtureSpec<'a> {
|
||||
name: &'a str,
|
||||
dir: &'a str,
|
||||
font: &'a str,
|
||||
font_size: u32,
|
||||
pages: u32,
|
||||
wer_target: f64,
|
||||
}
|
||||
|
|
@ -1,127 +0,0 @@
|
|||
#!/usr/bin/env python3
|
||||
"""
|
||||
Generate sensitive.pdf for TH-08 log audit test.
|
||||
|
||||
This script creates a password-protected PDF with unique, distinctive markers:
|
||||
- Body text contains "UNIQUE-MARKER-IN-BODY-TEXT-7f9a"
|
||||
- Password value is "UNIQUE-PASSWORD-FOR-TH08-7f9a"
|
||||
|
||||
These markers are specifically designed to be unlikely to appear
|
||||
in normal log output, making substring-based leak detection reliable.
|
||||
"""
|
||||
|
||||
import pikepdf
|
||||
import io
|
||||
|
||||
# Constants for unique markers
|
||||
BODY_TEXT = "UNIQUE-MARKER-IN-BODY-TEXT-7f9a"
|
||||
PASSWORD = "UNIQUE-PASSWORD-FOR-TH08-7f9a"
|
||||
|
||||
# Minimal PDF content with the unique marker
|
||||
MINIMAL_PDF = f"""%PDF-1.4
|
||||
1 0 obj
|
||||
<<
|
||||
/Type /Catalog
|
||||
/Pages 2 0 R
|
||||
>>
|
||||
endobj
|
||||
2 0 obj
|
||||
<<
|
||||
/Type /Pages
|
||||
/Count 1
|
||||
/Kids [3 0 R]
|
||||
>>
|
||||
endobj
|
||||
3 0 obj
|
||||
<<
|
||||
/Type /Page
|
||||
/Parent 2 0 R
|
||||
/MediaBox [0 0 612 792]
|
||||
/Resources <<
|
||||
/Font <<
|
||||
/F1 <<
|
||||
/Type /Font
|
||||
/Subtype /Type1
|
||||
/BaseFont /Helvetica
|
||||
>>
|
||||
>>
|
||||
>>
|
||||
/Contents 4 0 R
|
||||
>>
|
||||
endobj
|
||||
4 0 obj
|
||||
<<
|
||||
/Length {len(BODY_TEXT) + 30}
|
||||
>>
|
||||
stream
|
||||
BT
|
||||
/F1 12 Tf
|
||||
100 700 Td
|
||||
({BODY_TEXT}) Tj
|
||||
ET
|
||||
endstream
|
||||
endobj
|
||||
xref
|
||||
0 5
|
||||
0000000000 65535 f
|
||||
0000000009 00000 n
|
||||
0000000058 00000 n
|
||||
0000000115 00000 n
|
||||
0000000350 00000 n
|
||||
trailer
|
||||
<<
|
||||
/Size 5
|
||||
/Root 1 0 R
|
||||
>>
|
||||
startxref
|
||||
450
|
||||
%%EOF
|
||||
"""
|
||||
|
||||
def create_sensitive_pdf():
|
||||
"""Create a password-protected PDF with unique markers."""
|
||||
# Load the minimal PDF from bytes
|
||||
base_pdf = pikepdf.open(io.BytesIO(MINIMAL_PDF.encode()))
|
||||
|
||||
# Save with password protection
|
||||
output_path = "tests/fixtures/security/sensitive.pdf"
|
||||
base_pdf.save(
|
||||
output_path,
|
||||
encryption=pikepdf.Encryption(
|
||||
owner="",
|
||||
user=PASSWORD,
|
||||
R=2, # RC4-40 (widest compatibility)
|
||||
aes=False, # RC4 encryption for R=2
|
||||
allow=pikepdf.Permissions(
|
||||
accessibility=True,
|
||||
extract=True,
|
||||
modify_annotation=True,
|
||||
modify_assembly=False,
|
||||
modify_form=True,
|
||||
modify_other=True,
|
||||
print_lowres=True,
|
||||
print_highres=True
|
||||
),
|
||||
metadata=False # Can't encrypt metadata with R < 4
|
||||
)
|
||||
)
|
||||
|
||||
print(f"Created {output_path}")
|
||||
print(f" Password: {PASSWORD}")
|
||||
print(f" Body text marker: {BODY_TEXT}")
|
||||
|
||||
if __name__ == "__main__":
|
||||
import os
|
||||
|
||||
# Create security fixtures directory if it doesn't exist
|
||||
os.makedirs("tests/fixtures/security", exist_ok=True)
|
||||
|
||||
try:
|
||||
create_sensitive_pdf()
|
||||
print("\nSensitive fixture created successfully for TH-08 log audit test!")
|
||||
except Exception as e:
|
||||
print(f"Error: {e}")
|
||||
import traceback
|
||||
traceback.print_exc()
|
||||
print("\nNote: This script requires pikepdf.")
|
||||
print("Install with: pip install pikepdf")
|
||||
Loading…
Add table
Reference in a new issue