hohn/codeql
1
0
Fork 0
mirror of https://github.com/github/codeql.git synced 2025-12-21 11:16:30 +01:00
Code Issues Packages Projects Releases Wiki Activity

JS: Do not extract binary HTML

Browse Source
This commit is contained in:
Asger Feldthaus
2021-07-14 17:53:25 +02:00
parent 96a2c3f2db
commit b1ce3d1c5a
1 changed files with 34 additions and 29 deletions
Download Patch File Download Diff File Expand all files Collapse all files

63
javascript/extractor/src/com/semmle/js/extractor/FileExtractor.java
View File

@@ -114,6 +114,14 @@ public class FileExtractor {
public String toString() {
return "html";
}
@Override
protected boolean contains(File f, String lcExt, ExtractorConfig config) {
if (isBinaryFile(f, lcExt, config)) {
return false;
}
return super.contains(f, lcExt, config);
}
},
JS(".js", ".jsx", ".mjs", ".cjs", ".es6", ".es") {
@@ -152,32 +160,6 @@ public class FileExtractor {
public String toString() {
return "javascript";
}
/** Number of bytes to read from the beginning of a ".js" file to detect if it is a binary file. */
private static final int fileHeaderSize = 128;
/** Computes if `f` is a binary file based on whether the initial `fileHeaderSize` bytes are printable UTF-8 chars. */
private boolean isBinaryFile(File f, String lcExt, ExtractorConfig config) {
if (!config.getDefaultEncoding().equals(StandardCharsets.UTF_8.name())) {
return false;
}
try (FileInputStream fis = new FileInputStream(f)) {
byte[] bytes = new byte[fileHeaderSize];
int length = fis.read(bytes);
if (length == -1) return false;
// Avoid invalid or unprintable UTF-8 files.
if (hasUnprintableUtf8(bytes, length)) {
return true;
}
return false;
} catch (IOException e) {
Exceptions.ignore(e, "Let extractor handle this one.");
}
return false;
}
},
JSON(".json") {
@@ -234,9 +216,6 @@ public class FileExtractor {
return super.contains(f, lcExt, config);
}
/** Number of bytes to read from the beginning of a ".ts" file for sniffing its file type. */
private static final int fileHeaderSize = 128;
private boolean hasBadFileHeader(File f, String lcExt, ExtractorConfig config) {
if (!".ts".equals(lcExt)) {
return false;
@@ -348,6 +327,9 @@ public class FileExtractor {
}
};
/** Number of bytes to read from the beginning of a file to sniff its file type. */
private static final int fileHeaderSize = 128;
/** The file extensions (lower-case, including leading dot) corresponding to this file type. */
private final Set<String> extensions = new LinkedHashSet<String>();
@@ -398,6 +380,29 @@ public class FileExtractor {
return true;
}
/** Computes if `f` is a binary file based on whether the initial `fileHeaderSize` bytes are printable UTF-8 chars. */
public static boolean isBinaryFile(File f, String lcExt, ExtractorConfig config) {
if (!config.getDefaultEncoding().equals(StandardCharsets.UTF_8.name())) {
return false;
}
try (FileInputStream fis = new FileInputStream(f)) {
byte[] bytes = new byte[fileHeaderSize];
int length = fis.read(bytes);
if (length == -1) return false;
// Avoid invalid or unprintable UTF-8 files.
if (hasUnprintableUtf8(bytes, length)) {
return true;
}
return false;
} catch (IOException e) {
Exceptions.ignore(e, "Let extractor handle this one.");
}
return false;
}
/** The names of all defined {@linkplain FileType}s. */
public static final Set<String> allNames = new LinkedHashSet<String>();