Tweak how binary files are handled internally.

This commit fixes two issues. The first issue is that if a file contained
many NUL bytes without any LF bytes, then the InputBuffer would read the
entire file into memory. This is not typically a problem, but if you run
rg on /proc, then bad things can happen when reading virtual memory mapping
files. Arguably, such files should be ignored, but we should also try to
avoid exhausting memory too. We fix this by pushing the `-a/--text` flag
option down into InputBuffer, so that it knows to stop immediately if it
finds a NUL byte.

The other issue this fixes is that binary detection is now applied to every
buffer instead of just the first one. This helps avoid detecting too many
files as plain text if the first parts of a binary file happen to contain
no NUL bytes. This issue still persists somewhat in the memory map
searcher, since we probably don't want to search the entire file upfront
for NUL bytes before actually performing our search. Instead, we search the
first 10KB for now.

Fixes #52, Fixes #311

2 files changed, 24 insertions, 17 deletions

diff --git a/src/search_buffer.rs b/src/search_buffer.rs
index 2b792b5c..4745c2f8 100644
--- a/src/search_buffer.rs
+++ b/src/search_buffer.rs
@@ -113,8 +113,8 @@ impl<'a, W: WriteColor> BufferSearcher<'a, W> {
 
     #[inline(never)]
     pub fn run(mut self) -> u64 {
-        let binary_upto = cmp::min(4096, self.buf.len());
-        if !self.opts.text && is_binary(&self.buf[..binary_upto]) {
+        let binary_upto = cmp::min(10240, self.buf.len());
+        if !self.opts.text && is_binary(&self.buf[..binary_upto], true) {
             return 0;
         }
 
diff --git a/src/search_stream.rs b/src/search_stream.rs
index 16302922..e558c2d3 100644
--- a/src/search_stream.rs
+++ b/src/search_stream.rs
@@ -248,6 +248,7 @@ impl<'a, R: io::Read, W: WriteColor> Searcher<'a, R, W> {
     /// If enabled, search binary files as if they were text.
     pub fn text(mut self, yes: bool) -> Self {
         self.opts.text = yes;
+        self.inp.text(yes);
         self
     }
 
@@ -266,9 +267,6 @@ impl<'a, R: io::Read, W: WriteColor> Searcher<'a, R, W> {
             if !try!(self.fill()) {
                 break;
             }
-            if !self.opts.text && self.inp.is_binary {
-                break;
-            }
             while !self.terminate() && self.inp.pos < self.inp.lastnl {
                 let matched = self.grep.read_match(
                     &mut self.last_match,
@@ -501,10 +499,8 @@ pub struct InputBuffer {
     end: usize,
     /// Set to true if and only if no reads have occurred yet.
     first: bool,
-    /// Set to true if and only if the contents of buf are determined to be
-    /// "binary" (i.e., not searchable text). Note that its value may be
-    /// falsely negative *or* falsely positive. It is only a heuristic.
-    is_binary: bool,
+    /// Set to true if all binary data should be treated as if it were text.
+    text: bool,
 }
 
 impl InputBuffer {
@@ -532,13 +528,23 @@ impl InputBuffer {
             lastnl: 0,
             end: 0,
             first: true,
-            is_binary: false,
+            text: false,
         }
     }
 
     /// Set the end-of-line terminator used by this input buffer.
-    pub fn eol(&mut self, eol: u8) {
+    pub fn eol(&mut self, eol: u8) -> &mut Self {
         self.eol = eol;
+        self
+    }
+
+    /// If enabled, search binary files as if they were text.
+    ///
+    /// Note that this may cause the buffer to load the entire contents of a
+    /// file into memory.
+    pub fn text(&mut self, yes: bool) -> &mut Self {
+        self.text = yes;
+        self
     }
 
     /// Resets this buffer so that it may be reused with a new reader.
@@ -547,7 +553,6 @@ impl InputBuffer {
         self.lastnl = 0;
         self.end = 0;
         self.first = true;
-        self.is_binary = false;
     }
 
     /// Fill the contents of this buffer with the reader given. The reader
@@ -582,8 +587,10 @@ impl InputBuffer {
             }
             let n = try!(rdr.read(
                 &mut self.buf[self.end..self.end + self.read_size]));
-            if self.first && is_binary(&self.buf[self.end..self.end + n]) {
-                self.is_binary = true;
+            if !self.text {
+                if is_binary(&self.buf[self.end..self.end + n], self.first) {
+                    return Ok(false);
+                }
             }
             self.first = false;
             // We assume that reading 0 bytes means we've hit EOF.
@@ -613,11 +620,11 @@ impl InputBuffer {
 ///
 /// Note that this may return both false positives and false negatives.
 #[inline(always)]
-pub fn is_binary(buf: &[u8]) -> bool {
-    if buf.len() >= 4 && &buf[0..4] == b"%PDF" {
+pub fn is_binary(buf: &[u8], first: bool) -> bool {
+    if first && buf.len() >= 4 && &buf[0..4] == b"%PDF" {
         return true;
     }
-    memchr(b'\x00', &buf[0..cmp::min(1024, buf.len())]).is_some()
+    memchr(b'\x00', buf).is_some()
 }
 
 /// Count the number of lines in the given buffer.