Binary and CR-LF detection: lone CRs -> binary

C git considers not only files containing NUL bytes as binary but also
files containing lone CRs. Implement this also for JGit.

C git additionally counts printable vs. non-printable characters and
considers files that have non_printable_count > printable_count / 128
also as binary. This is not implemented because such counting probably
only makes sense if one looks at the full file or blob content. The
Auto[CR]LF* streams in JGit look only at the first few KiB of a stream
in order not to buffer too much.

For the C git implementation, see [1].

[1] https://github.com/git/git/blob/7e27bd589d/convert.c#L35

Bug: 576971
Change-Id: Ia169b59bdbf1477f32ee2014eeb8406f81d4b1ab
Signed-off-by: Thomas Wolf <thomas.wolf@paranor.ch>

4 files changed, 19 insertions, 16 deletions

diff --git a/org.eclipse.jgit/src/org/eclipse/jgit/util/io/AutoCRLFInputStream.java b/org.eclipse.jgit/src/org/eclipse/jgit/util/io/AutoCRLFInputStream.java
index 1b03d097b6..cedb159827 100644
--- a/org.eclipse.jgit/src/org/eclipse/jgit/util/io/AutoCRLFInputStream.java
+++ b/org.eclipse.jgit/src/org/eclipse/jgit/util/io/AutoCRLFInputStream.java
@@ -123,7 +123,7 @@ public class AutoCRLFInputStream extends InputStream {
 			return false;
 		}
 		if (detectBinary) {
-			isBinary = RawText.isBinary(buf, cnt);
+			isBinary = RawText.isBinary(buf, cnt, cnt < buf.length);
 			detectBinary = false;
 		}
 		ptr = 0;
diff --git a/org.eclipse.jgit/src/org/eclipse/jgit/util/io/AutoCRLFOutputStream.java b/org.eclipse.jgit/src/org/eclipse/jgit/util/io/AutoCRLFOutputStream.java
index 05e271febd..e638b2de3a 100644
--- a/org.eclipse.jgit/src/org/eclipse/jgit/util/io/AutoCRLFOutputStream.java
+++ b/org.eclipse.jgit/src/org/eclipse/jgit/util/io/AutoCRLFOutputStream.java
@@ -122,22 +122,24 @@ public class AutoCRLFOutputStream extends OutputStream {
 	}
 
 	private int buffer(byte[] b, int off, int len) throws IOException {
-		if (binbufcnt > binbuf.length)
+		if (binbufcnt > binbuf.length) {
 			return len;
+		}
 		int copy = Math.min(binbuf.length - binbufcnt, len);
 		System.arraycopy(b, off, binbuf, binbufcnt, copy);
 		binbufcnt += copy;
 		int remaining = len - copy;
-		if (remaining > 0)
-			decideMode();
+		if (remaining > 0) {
+			decideMode(false);
+		}
 		return remaining;
 	}
 
-	private void decideMode() throws IOException {
+	private void decideMode(boolean complete) throws IOException {
 		if (detectBinary) {
-			isBinary = RawText.isBinary(binbuf, binbufcnt);
+			isBinary = RawText.isBinary(binbuf, binbufcnt, complete);
 			if (!isBinary) {
-				isBinary = RawText.isCrLfText(binbuf, binbufcnt);
+				isBinary = RawText.isCrLfText(binbuf, binbufcnt, complete);
 			}
 			detectBinary = false;
 		}
@@ -149,8 +151,9 @@ public class AutoCRLFOutputStream extends OutputStream {
 	/** {@inheritDoc} */
 	@Override
 	public void flush() throws IOException {
-		if (binbufcnt <= binbuf.length)
-			decideMode();
+		if (binbufcnt <= binbuf.length) {
+			decideMode(true);
+		}
 		buf = -1;
 		out.flush();
 	}
diff --git a/org.eclipse.jgit/src/org/eclipse/jgit/util/io/AutoLFInputStream.java b/org.eclipse.jgit/src/org/eclipse/jgit/util/io/AutoLFInputStream.java
index b6d1848b3a..7db882c074 100644
--- a/org.eclipse.jgit/src/org/eclipse/jgit/util/io/AutoLFInputStream.java
+++ b/org.eclipse.jgit/src/org/eclipse/jgit/util/io/AutoLFInputStream.java
@@ -262,14 +262,14 @@ public class AutoLFInputStream extends InputStream {
 			return false;
 		}
 		if (detectBinary) {
-			isBinary = RawText.isBinary(buf, cnt);
+			isBinary = RawText.isBinary(buf, cnt, cnt < buf.length);
 			passAsIs = isBinary;
 			detectBinary = false;
 			if (isBinary && abortIfBinary) {
 				throw new IsBinaryException();
 			}
 			if (!passAsIs && forCheckout) {
-				passAsIs = RawText.isCrLfText(buf, cnt);
+				passAsIs = RawText.isCrLfText(buf, cnt, cnt < buf.length);
 			}
 		}
 		ptr = 0;
diff --git a/org.eclipse.jgit/src/org/eclipse/jgit/util/io/AutoLFOutputStream.java b/org.eclipse.jgit/src/org/eclipse/jgit/util/io/AutoLFOutputStream.java
index e08a53f502..a0e9fb68c5 100644
--- a/org.eclipse.jgit/src/org/eclipse/jgit/util/io/AutoLFOutputStream.java
+++ b/org.eclipse.jgit/src/org/eclipse/jgit/util/io/AutoLFOutputStream.java
@@ -146,16 +146,16 @@ public class AutoLFOutputStream extends OutputStream {
 		binbufcnt += copy;
 		int remaining = len - copy;
 		if (remaining > 0) {
-			decideMode();
+			decideMode(false);
 		}
 		return remaining;
 	}
 
-	private void decideMode() throws IOException {
+	private void decideMode(boolean complete) throws IOException {
 		if (detectBinary) {
-			isBinary = RawText.isBinary(binbuf, binbufcnt);
+			isBinary = RawText.isBinary(binbuf, binbufcnt, complete);
 			if (!isBinary) {
-				isBinary = RawText.isCrLfText(binbuf, binbufcnt);
+				isBinary = RawText.isCrLfText(binbuf, binbufcnt, complete);
 			}
 			detectBinary = false;
 		}
@@ -168,7 +168,7 @@ public class AutoLFOutputStream extends OutputStream {
 	@Override
 	public void flush() throws IOException {
 		if (binbufcnt <= binbuf.length) {
-			decideMode();
+			decideMode(true);
 		}
 		out.flush();
 	}