mirror of
https://github.com/norandom/OpenUltraSAST.git
synced 2026-10-21 14:09:27 +00:00
feat(pair-corpus-honesty): add vibe-py, vfc-js and agent-vfc slices with mechanism vocabulary
Tasks 1.1, 5.1, 5.2, 5.4 and the data half of 5.3. - mechanisms.toml: closed vocabulary v1 (20 ids) every expected row cites. - vibe-py: 35 Real-Vuln-Benchmark pairs (Apache-2.0), human provenance only because the LLM-generated repositories carry no license (escalated). - vfc-js: 17 Node fix-commit pairs harvested upstream (MIT/Apache-2.0), SecBench.js itself is not vendored (no license); sinks derived on 13/17. - agent-vfc: 29 agent-trailer fixes as catalog-candidates.toml plus REVIEW.md; the loaded catalog stays empty until a human reviews them. - datasets.toml and README document every slice and its review status. Co-Authored-By: Claude Fable 5.1 <[email protected]> Claude-Session: https://claude.ai/code/session_01T7XD7x5KonMdmGRkp63EQG
This commit is contained in:
Marius Ciepluch
co-authored by
Claude Fable 5.1
Claude Fable 5.1
parent
c3e841003c
commit
8ab4207618
@@ -0,0 +1,214 @@
|
||||
// Provenance: roest01/node-pdf-image (fixed).
|
||||
// repo: roest01/node-pdf-image
|
||||
// commit: 54679496a89738443917608c2bbe2f6e5dd20e83
|
||||
// parent: d8c0dcadd93985dbefe80b84060f5f572bfbb6ff
|
||||
// commit_url: https://github.com/roest01/node-pdf-image/commit/54679496a89738443917608c2bbe2f6e5dd20e83
|
||||
// cve: CVE-2018-3757
|
||||
// license: MIT
|
||||
// function: getInfo
|
||||
// relpath: index.js
|
||||
// provenance: human
|
||||
// mechanism: source_reaches_sink
|
||||
// upstream_start: 24
|
||||
|
||||
PDFImage.prototype = {
|
||||
constructGetInfoCommand: function () {
|
||||
return {
|
||||
cmd: "pdfinfo",
|
||||
args: [this.pdfFilePath]
|
||||
};
|
||||
},
|
||||
parseGetInfoCommandOutput: function (output) {
|
||||
var info = {};
|
||||
output.split("\n").forEach(function (line) {
|
||||
if (line.match(/^(.*?):[ \t]*(.*)$/)) {
|
||||
info[RegExp.$1] = RegExp.$2;
|
||||
}
|
||||
});
|
||||
return info;
|
||||
},
|
||||
getInfo: function () {
|
||||
var self = this;
|
||||
var getInfoCommand = this.constructGetInfoCommand();
|
||||
return new Promise(function (resolve, reject) {
|
||||
spawn(getInfoCommand.cmd, getInfoCommand.args, { capture: [ 'stdout', 'stderr' ]})
|
||||
.then(function (cmdResult) {
|
||||
resolve(self.parseGetInfoCommandOutput(cmdResult.stdout.toString()));
|
||||
}).catch(reject);
|
||||
});
|
||||
},
|
||||
numberOfPages: function () {
|
||||
return this.getInfo().then(function (info) {
|
||||
return info["Pages"];
|
||||
});
|
||||
},
|
||||
getOutputImagePathForPage: function (pageNumber) {
|
||||
return path.join(
|
||||
this.outputDirectory,
|
||||
this.pdfFileBaseName + "-" + pageNumber + "." + this.convertExtension
|
||||
);
|
||||
},
|
||||
getOutputImagePathForFile: function () {
|
||||
return path.join(
|
||||
this.outputDirectory,
|
||||
this.pdfFileBaseName + "." + this.convertExtension
|
||||
);
|
||||
},
|
||||
setConvertOptions: function (convertOptions) {
|
||||
this.convertOptions = convertOptions || {};
|
||||
},
|
||||
setPdfFileBaseName: function(pdfFileBaseName) {
|
||||
this.pdfFileBaseName = pdfFileBaseName || path.basename(this.pdfFilePath, ".pdf");
|
||||
},
|
||||
setConvertExtension: function (convertExtension) {
|
||||
this.convertExtension = convertExtension || "png";
|
||||
},
|
||||
constructConvertCommandForPage: function (pageNumber) {
|
||||
var pdfFilePath = this.pdfFilePath;
|
||||
var outputImagePath = this.getOutputImagePathForPage(pageNumber);
|
||||
var convertOptions = this.constructConvertOptions();
|
||||
var args = [];
|
||||
if (convertOptions) args = convertOptions.slice();
|
||||
args.push(pdfFilePath+"["+pageNumber+"]");
|
||||
args.push(outputImagePath);
|
||||
|
||||
return {
|
||||
cmd: this.useGM ? "gm convert" : "convert",
|
||||
args: args
|
||||
};
|
||||
},
|
||||
constructCombineCommandForFile: function (imagePaths) {
|
||||
var args = imagePaths.slice();
|
||||
args.push(this.getOutputImagePathForFile());
|
||||
args.unshift("-append");
|
||||
return {
|
||||
cmd: this.useGM ? "gm convert" : "convert",
|
||||
args: args
|
||||
};
|
||||
},
|
||||
constructConvertOptions: function () {
|
||||
var convertOptions = [];
|
||||
Object.keys(this.convertOptions).sort().map(function (optionName) {
|
||||
if (this.convertOptions[optionName] !== null) {
|
||||
convertOptions.push(optionName);
|
||||
convertOptions.push(this.convertOptions[optionName]);
|
||||
} else {
|
||||
convertOptions.push(optionName);
|
||||
}
|
||||
}, this);
|
||||
return convertOptions;
|
||||
},
|
||||
combineImages: function(imagePaths) {
|
||||
var pdfImage = this;
|
||||
var combineCommand = pdfImage.constructCombineCommandForFile(imagePaths);
|
||||
return new Promise(function (resolve, reject) {
|
||||
spawn(combineCommand.cmd, combineCommand.args, { capture: [ 'stdout', 'stderr' ]})
|
||||
.then(function () {
|
||||
spawn("rm", imagePaths); //cleanUp
|
||||
resolve(pdfImage.getOutputImagePathForFile());
|
||||
}).catch(function(error){
|
||||
reject({
|
||||
message: "Failed to combine images",
|
||||
error: error.message,
|
||||
stdout: error.stdout,
|
||||
stderr: error.stderr
|
||||
});
|
||||
});
|
||||
});
|
||||
},
|
||||
convertFile: function () {
|
||||
var pdfImage = this;
|
||||
return new Promise(function (resolve, reject) {
|
||||
pdfImage.numberOfPages().then(function (totalPages) {
|
||||
var convertPromise = new Promise(function (resolve, reject){
|
||||
var imagePaths = [];
|
||||
for (var i = 0; i < totalPages; i++) {
|
||||
pdfImage.convertPage(i).then(function(imagePath){
|
||||
imagePaths.push(imagePath);
|
||||
if (imagePaths.length === parseInt(totalPages)){
|
||||
imagePaths.sort(); //because of asyc pages we have to reSort pages
|
||||
resolve(imagePaths);
|
||||
}
|
||||
}).catch(function(error){
|
||||
reject(error);
|
||||
});
|
||||
}
|
||||
});
|
||||
|
||||
convertPromise.then(function(imagePaths){
|
||||
if (pdfImage.combinedImage){
|
||||
pdfImage.combineImages(imagePaths).then(function(imagePath){
|
||||
resolve(imagePath);
|
||||
});
|
||||
} else {
|
||||
resolve(imagePaths);
|
||||
}
|
||||
}).catch(function(error){
|
||||
reject(error);
|
||||
});
|
||||
});
|
||||
});
|
||||
},
|
||||
convertPage: function (pageNumber) {
|
||||
var pdfFilePath = this.pdfFilePath;
|
||||
var outputImagePath = this.getOutputImagePathForPage(pageNumber);
|
||||
var convertCommand = this.constructConvertCommandForPage(pageNumber);
|
||||
|
||||
var promise = new Promise(function (resolve, reject) {
|
||||
function convertPageToImage() {
|
||||
return new Promise(function (resolve, reject) {
|
||||
spawn(convertCommand.cmd, convertCommand.args, { capture: [ 'stdout', 'stderr' ]})
|
||||
.then(function () {
|
||||
resolve(outputImagePath);
|
||||
}).catch(function(error){
|
||||
reject({
|
||||
message: "Failed to convert page to image",
|
||||
error: error.message,
|
||||
stdout: error.stdout,
|
||||
stderr: error.stderr
|
||||
});
|
||||
});
|
||||
});
|
||||
}
|
||||
|
||||
fs.stat(outputImagePath, function (err, imageFileStat) {
|
||||
var imageNotExists = err && err.code === "ENOENT";
|
||||
if (!imageNotExists && err) {
|
||||
return reject({
|
||||
message: "Failed to stat image file",
|
||||
error: err
|
||||
});
|
||||
}
|
||||
|
||||
// convert when (1) image doesn't exits or (2) image exists
|
||||
// but its timestamp is older than pdf's one
|
||||
|
||||
if (imageNotExists) {
|
||||
// (1)
|
||||
convertPageToImage().then(function(result){
|
||||
resolve(result);
|
||||
}).catch(reject);
|
||||
return;
|
||||
}
|
||||
|
||||
// image exist. check timestamp.
|
||||
fs.stat(pdfFilePath, function (err, pdfFileStat) {
|
||||
if (err) {
|
||||
return reject({
|
||||
message: "Failed to stat PDF file",
|
||||
error: err
|
||||
});
|
||||
}
|
||||
|
||||
if (imageFileStat.mtime < pdfFileStat.mtime) {
|
||||
// (2)
|
||||
convertPageToImage().then(function(result){
|
||||
resolve(result);
|
||||
}).catch(reject);
|
||||
}
|
||||
});
|
||||
});
|
||||
});
|
||||
return promise;
|
||||
}
|
||||
};
|
||||
@@ -0,0 +1,212 @@
|
||||
// Provenance: roest01/node-pdf-image (vuln).
|
||||
// repo: roest01/node-pdf-image
|
||||
// commit: d8c0dcadd93985dbefe80b84060f5f572bfbb6ff
|
||||
// parent: d8c0dcadd93985dbefe80b84060f5f572bfbb6ff
|
||||
// commit_url: https://github.com/roest01/node-pdf-image/commit/54679496a89738443917608c2bbe2f6e5dd20e83
|
||||
// cve: CVE-2018-3757
|
||||
// license: MIT
|
||||
// function: getInfo
|
||||
// relpath: index.js
|
||||
// provenance: human
|
||||
// mechanism: source_reaches_sink
|
||||
// upstream_start: 24
|
||||
|
||||
PDFImage.prototype = {
|
||||
constructGetInfoCommand: function () {
|
||||
return util.format(
|
||||
"pdfinfo \"%s\"",
|
||||
this.pdfFilePath
|
||||
);
|
||||
},
|
||||
parseGetInfoCommandOutput: function (output) {
|
||||
var info = {};
|
||||
output.split("\n").forEach(function (line) {
|
||||
if (line.match(/^(.*?):[ \t]*(.*)$/)) {
|
||||
info[RegExp.$1] = RegExp.$2;
|
||||
}
|
||||
});
|
||||
return info;
|
||||
},
|
||||
getInfo: function () {
|
||||
var self = this;
|
||||
var getInfoCommand = this.constructGetInfoCommand();
|
||||
var promise = new Promise(function (resolve, reject) {
|
||||
exec(getInfoCommand, function (err, stdout, stderr) {
|
||||
if (err) {
|
||||
return reject({
|
||||
message: "Failed to get PDF'S information",
|
||||
error: err,
|
||||
stdout: stdout,
|
||||
stderr: stderr
|
||||
});
|
||||
}
|
||||
return resolve(self.parseGetInfoCommandOutput(stdout));
|
||||
});
|
||||
});
|
||||
return promise;
|
||||
},
|
||||
numberOfPages: function () {
|
||||
return this.getInfo().then(function (info) {
|
||||
return info["Pages"];
|
||||
});
|
||||
},
|
||||
getOutputImagePathForPage: function (pageNumber) {
|
||||
return path.join(
|
||||
this.outputDirectory,
|
||||
this.pdfFileBaseName + "-" + pageNumber + "." + this.convertExtension
|
||||
);
|
||||
},
|
||||
getOutputImagePathForFile: function () {
|
||||
return path.join(
|
||||
this.outputDirectory,
|
||||
this.pdfFileBaseName + "." + this.convertExtension
|
||||
);
|
||||
},
|
||||
setConvertOptions: function (convertOptions) {
|
||||
this.convertOptions = convertOptions || {};
|
||||
},
|
||||
setPdfFileBaseName: function(pdfFileBaseName) {
|
||||
this.pdfFileBaseName = pdfFileBaseName || path.basename(this.pdfFilePath, ".pdf");
|
||||
},
|
||||
setConvertExtension: function (convertExtension) {
|
||||
this.convertExtension = convertExtension || "png";
|
||||
},
|
||||
constructConvertCommandForPage: function (pageNumber) {
|
||||
var pdfFilePath = this.pdfFilePath;
|
||||
var outputImagePath = this.getOutputImagePathForPage(pageNumber);
|
||||
var convertOptionsString = this.constructConvertOptions();
|
||||
return util.format(
|
||||
"%s %s\"%s[%d]\" \"%s\"",
|
||||
this.useGM ? "gm convert" : "convert",
|
||||
convertOptionsString ? convertOptionsString + " " : "",
|
||||
pdfFilePath, pageNumber, outputImagePath
|
||||
);
|
||||
},
|
||||
constructCombineCommandForFile: function (imagePaths) {
|
||||
return util.format(
|
||||
"%s -append %s \"%s\"",
|
||||
this.useGM ? "gm convert" : "convert",
|
||||
imagePaths.join(' '),
|
||||
this.getOutputImagePathForFile()
|
||||
);
|
||||
},
|
||||
constructConvertOptions: function () {
|
||||
return Object.keys(this.convertOptions).sort().map(function (optionName) {
|
||||
if (this.convertOptions[optionName] !== null) {
|
||||
return optionName + " " + this.convertOptions[optionName];
|
||||
} else {
|
||||
return optionName;
|
||||
}
|
||||
}, this).join(" ");
|
||||
},
|
||||
combineImages: function(imagePaths) {
|
||||
var pdfImage = this;
|
||||
var combineCommand = pdfImage.constructCombineCommandForFile(imagePaths);
|
||||
return new Promise(function (resolve, reject) {
|
||||
exec(combineCommand, function (err, stdout, stderr) {
|
||||
if (err) {
|
||||
return reject({
|
||||
message: "Failed to combine images",
|
||||
error: err,
|
||||
stdout: stdout,
|
||||
stderr: stderr
|
||||
});
|
||||
}
|
||||
exec("rm "+imagePaths.join(' ')); //cleanUp
|
||||
return resolve(pdfImage.getOutputImagePathForFile());
|
||||
});
|
||||
});
|
||||
},
|
||||
convertFile: function () {
|
||||
var pdfImage = this;
|
||||
return new Promise(function (resolve, reject) {
|
||||
pdfImage.numberOfPages().then(function (totalPages) {
|
||||
var convertPromise = new Promise(function (resolve, reject){
|
||||
var imagePaths = [];
|
||||
for (var i = 0; i < totalPages; i++) {
|
||||
pdfImage.convertPage(i).then(function(imagePath){
|
||||
imagePaths.push(imagePath);
|
||||
if (imagePaths.length === parseInt(totalPages)){
|
||||
imagePaths.sort(); //because of asyc pages we have to reSort pages
|
||||
resolve(imagePaths);
|
||||
}
|
||||
}).catch(function(error){
|
||||
reject(error);
|
||||
});
|
||||
}
|
||||
});
|
||||
|
||||
convertPromise.then(function(imagePaths){
|
||||
if (pdfImage.combinedImage){
|
||||
pdfImage.combineImages(imagePaths).then(function(imagePath){
|
||||
resolve(imagePath);
|
||||
});
|
||||
} else {
|
||||
resolve(imagePaths);
|
||||
}
|
||||
}).catch(function(error){
|
||||
reject(error);
|
||||
});
|
||||
});
|
||||
});
|
||||
},
|
||||
convertPage: function (pageNumber) {
|
||||
var pdfFilePath = this.pdfFilePath;
|
||||
var outputImagePath = this.getOutputImagePathForPage(pageNumber);
|
||||
var convertCommand = this.constructConvertCommandForPage(pageNumber);
|
||||
|
||||
var promise = new Promise(function (resolve, reject) {
|
||||
function convertPageToImage() {
|
||||
exec(convertCommand, function (err, stdout, stderr) {
|
||||
if (err) {
|
||||
return reject({
|
||||
message: "Failed to convert page to image",
|
||||
error: err,
|
||||
stdout: stdout,
|
||||
stderr: stderr
|
||||
});
|
||||
}
|
||||
return resolve(outputImagePath);
|
||||
});
|
||||
}
|
||||
|
||||
fs.stat(outputImagePath, function (err, imageFileStat) {
|
||||
var imageNotExists = err && err.code === "ENOENT";
|
||||
if (!imageNotExists && err) {
|
||||
return reject({
|
||||
message: "Failed to stat image file",
|
||||
error: err
|
||||
});
|
||||
}
|
||||
|
||||
// convert when (1) image doesn't exits or (2) image exists
|
||||
// but its timestamp is older than pdf's one
|
||||
|
||||
if (imageNotExists) {
|
||||
// (1)
|
||||
convertPageToImage();
|
||||
return;
|
||||
}
|
||||
|
||||
// image exist. check timestamp.
|
||||
fs.stat(pdfFilePath, function (err, pdfFileStat) {
|
||||
if (err) {
|
||||
return reject({
|
||||
message: "Failed to stat PDF file",
|
||||
error: err
|
||||
});
|
||||
}
|
||||
|
||||
if (imageFileStat.mtime < pdfFileStat.mtime) {
|
||||
// (2)
|
||||
convertPageToImage();
|
||||
return;
|
||||
}
|
||||
|
||||
return resolve(outputImagePath);
|
||||
});
|
||||
});
|
||||
});
|
||||
return promise;
|
||||
}
|
||||
};
|
||||
Reference in New Issue
Block a user