Linguist 2.3.3

When testing if a blob is indexable or safe to colorize, check size first

github-linguist.gemspec

@@ -1,6 +1,6 @@
 Gem::Specification.new do |s|
   s.name    = 'github-linguist'
-  s.version = '2.3.1'
+  s.version = '2.3.3'
   s.summary = "GitHub Language detection"
 
   s.authors = "GitHub"
@@ -12,6 +12,7 @@ Gem::Specification.new do |s|
   s.add_dependency 'escape_utils',    '~> 0.2.3'
   s.add_dependency 'mime-types',      '~> 1.19'
   s.add_dependency 'pygments.rb',     '>= 0.2.13'
+  s.add_development_dependency 'mocha'
   s.add_development_dependency 'json'
   s.add_development_dependency 'rake'
   s.add_development_dependency 'yajl-ruby'

lib/linguist/blob_helper.rb

@@ -160,7 +160,7 @@ module Linguist
     #
     # Return true or false
     def safe_to_colorize?
-      text? && !large? && !high_ratio_of_long_lines?
+      !large? && text? && !high_ratio_of_long_lines?
     end
 
     # Internal: Does the blob have a ratio of long lines?
@@ -250,7 +250,9 @@ module Linguist
     #
     # Return true or false
     def indexable?
-      if binary?
+      if size > 100 * 1024
+        false
+      elsif binary?
         false
       elsif extname == '.txt'
         true
@@ -260,8 +262,6 @@ module Linguist
         false
       elsif generated?
         false
-      elsif size > 100 * 1024
-        false
       else
         true
       end

lib/linguist/samples.json

@@ -257,8 +257,8 @@
       ".gemrc"
     ]
   },
-  "tokens_total": 269398,
+  "tokens_total": 270906,
-  "languages_total": 274,
+  "languages_total": 275,
   "tokens": {
     "Apex": {
       "global": 70,
@@ -25170,23 +25170,23 @@
       "/": 2
     },
     "Shell": {
-      "SHEBANG#!bash": 5,
+      "SHEBANG#!bash": 6,
-      "echo": 20,
+      "echo": 52,
       "export": 6,
       "PATH": 5,
       "pkgname": 1,
       "stud": 4,
-      "-": 42,
+      "-": 182,
       "git": 9,
       "pkgver": 1,
       "pkgrel": 1,
       "pkgdesc": 1,
       "arch": 1,
-      "(": 16,
+      "(": 89,
       "i686": 1,
       "x86_64": 1,
-      ")": 19,
+      ")": 134,
-      "url": 1,
+      "url": 4,
       "license": 1,
       "depends": 1,
       "libev": 1,
@@ -25198,26 +25198,26 @@
       "https": 1,
       "//github.com/bumptech/stud.git": 1,
       "_gitname": 1,
-      "build": 1,
+      "build": 2,
-      "{": 5,
+      "{": 49,
       "cd": 4,
       "msg": 4,
-      "if": 15,
+      "if": 27,
-      "[": 24,
+      "[": 70,
-      "d": 4,
+      "d": 7,
-      "]": 24,
+      "]": 70,
-      ";": 16,
+      ";": 115,
-      "then": 17,
+      "then": 29,
-      "&&": 4,
+      "&&": 54,
       "pull": 3,
       "origin": 1,
-      "else": 6,
+      "else": 10,
       "clone": 2,
-      "fi": 15,
+      "fi": 24,
       "rm": 2,
       "rf": 1,
       "make": 2,
-      "}": 5,
+      "}": 47,
       "package": 1,
       "PREFIX": 1,
       "/usr": 1,
@@ -25225,21 +25225,21 @@
       "install": 2,
       "Dm755": 1,
       "init.stud": 1,
-      "mkdir": 1,
+      "mkdir": 2,
-      "p": 1,
+      "p": 2,
-      "#": 9,
+      "#": 11,
       "Bash": 1,
       "script": 1,
-      "to": 4,
+      "to": 15,
-      "the": 3,
+      "the": 9,
       "dotfile": 1,
-      "repository": 2,
+      "repository": 3,
       "does": 1,
-      "a": 2,
+      "a": 7,
       "lot": 1,
-      "of": 1,
+      "of": 2,
       "fun": 2,
-      "stuff": 2,
+      "stuff": 3,
       "like": 1,
       "turning": 1,
       "normal": 1,
@@ -25248,11 +25248,11 @@
       ".bashrc": 1,
       "into": 1,
       "symlinks": 1,
-      "this": 1,
+      "this": 4,
       "away": 1,
       "optionally": 1,
       "moving": 1,
-      "old": 1,
+      "old": 4,
       "files": 1,
       "so": 1,
       "that": 1,
@@ -25260,7 +25260,7 @@
       "can": 1,
       "be": 1,
       "preserved": 1,
-      "setting": 1,
+      "setting": 2,
       "up": 1,
       "cron": 1,
       "job": 1,
@@ -25271,38 +25271,38 @@
       "some": 1,
       "more": 1,
       "shopt": 1,
-      "s": 2,
+      "s": 6,
       "nocasematch": 1,
       "This": 1,
       "makes": 1,
       "pattern": 1,
       "matching": 1,
-      "case": 2,
+      "case": 8,
       "insensitive": 1,
       "POSTFIX": 1,
       "URL": 1,
       "PUSHURL": 1,
       "overwrite": 3,
-      "true": 1,
+      "true": 2,
       "print_help": 2,
-      "e": 2,
+      "e": 4,
-      "exit": 7,
+      "exit": 9,
-      "for": 3,
+      "for": 5,
-      "opt": 2,
+      "opt": 3,
-      "in": 4,
+      "in": 14,
-      "@": 1,
+      "@": 3,
-      "do": 3,
+      "do": 7,
       "k": 1,
-      "|": 2,
+      "|": 14,
       "keep": 1,
-      "local": 3,
+      "local": 22,
       "false": 2,
-      "h": 1,
+      "h": 3,
-      "help": 1,
+      "help": 3,
-      "esac": 1,
+      "esac": 6,
-      "done": 3,
+      "done": 7,
-      "f": 3,
+      "f": 11,
-      ".*": 1,
+      ".*": 2,
       "o": 3,
       "continue": 1,
       "mv": 1,
@@ -25314,35 +25314,296 @@
       ".jobs.cron": 1,
       "source": 3,
       "/.bashrc": 1,
-      "set": 2,
+      "set": 9,
-      "n": 2,
+      "n": 7,
       "x": 1,
-      "unset": 3,
+      "unset": 6,
       "system": 1,
-      "exec": 1,
+      "exec": 3,
       "rbenv": 2,
       "versions": 1,
       "bare": 1,
-      "version": 1,
+      "version": 11,
-      "z": 3,
+      "z": 4,
-      "&": 4,
+      "&": 5,
       "prefix": 1,
-      "/dev/null": 2,
+      "/dev/null": 6,
       "rvm_ignore_rvmrc": 1,
-      "declare": 1,
+      "declare": 22,
       "rvmrc": 3,
       "rvm_rvmrc_files": 3,
       "ef": 1,
       "+": 1,
       "GREP_OPTIONS": 1,
-      "grep": 1,
+      "grep": 6,
-      "printf": 1,
+      "printf": 4,
       "rvm_path": 4,
       "UID": 1,
-      "elif": 2,
+      "elif": 4,
       "rvm_is_not_a_shell_function": 2,
       "rvm_path/scripts": 1,
       "rvm": 1,
+      "r": 15,
+      "sbt_release_version": 2,
+      "sbt_snapshot_version": 2,
+      "SNAPSHOT": 3,
+      "sbt_jar": 3,
+      "sbt_dir": 2,
+      "sbt_create": 2,
+      "sbt_snapshot": 1,
+      "sbt_launch_dir": 3,
+      "scala_version": 3,
+      "java_home": 1,
+      "sbt_explicit_version": 7,
+      "verbose": 6,
+      "debug": 11,
+      "quiet": 6,
+      "build_props_sbt": 3,
+      "project/build.properties": 9,
+      "versionLine": 2,
+      "sbt.version": 3,
+      "versionString": 3,
+      "versionLine##sbt.version": 1,
+      "update_build_props_sbt": 2,
+      "ver": 5,
+      "return": 3,
+      "perl": 3,
+      "pi": 1,
+      "q": 4,
+      "||": 12,
+      "Updated": 1,
+      "file": 3,
+      "Previous": 1,
+      "value": 1,
+      "was": 1,
+      "sbt_version": 8,
+      "v": 5,
+      "echoerr": 3,
+      "vlog": 1,
+      "dlog": 8,
+      "get_script_path": 2,
+      "path": 11,
+      "L": 1,
+      "target": 1,
+      "readlink": 1,
+      "get_mem_opts": 3,
+      "mem": 4,
+      "perm": 6,
+      "/": 2,
+      "<": 2,
+      "codecache": 1,
+      "die": 2,
+      "make_url": 3,
+      "groupid": 1,
+      "category": 1,
+      "default_jvm_opts": 1,
+      "default_sbt_opts": 1,
+      "default_sbt_mem": 2,
+      "noshare_opts": 1,
+      "sbt_opts_file": 1,
+      "jvm_opts_file": 1,
+      "latest_28": 1,
+      "latest_29": 1,
+      "latest_210": 1,
+      "script_path": 1,
+      "script_dir": 1,
+      "script_name": 2,
+      "java_cmd": 2,
+      "java": 2,
+      "sbt_mem": 5,
+      "residual_args": 4,
+      "java_args": 3,
+      "scalac_args": 4,
+      "sbt_commands": 2,
+      "build_props_scala": 1,
+      "build.scala.versions": 1,
+      "versionLine##build.scala.versions": 1,
+      "%": 3,
+      "execRunner": 2,
+      "arg": 3,
+      "sbt_groupid": 3,
+      "*": 11,
+      "org.scala": 4,
+      "tools.sbt": 3,
+      "sbt": 18,
+      "sbt_artifactory_list": 2,
+      "version0": 2,
+      "curl": 4,
+      "list": 1,
+      "only": 2,
+      "F": 1,
+      "pe": 1,
+      "make_release_url": 2,
+      "releases": 1,
+      "make_snapshot_url": 2,
+      "snapshots": 1,
+      "head": 1,
+      "jar_url": 1,
+      "jar_file": 1,
+      "download_url": 2,
+      "jar": 3,
+      "dirname": 1,
+      "which": 4,
+      "fail": 1,
+      "silent": 1,
+      "output": 1,
+      "wget": 2,
+      "O": 1,
+      "acquire_sbt_jar": 1,
+      "sbt_url": 1,
+      "usage": 2,
+      "cat": 3,
+      "<<": 2,
+      "EOM": 3,
+      "Usage": 1,
+      "options": 4,
+      "print": 1,
+      "message": 1,
+      "runner": 1,
+      "is": 5,
+      "chattier": 1,
+      "log": 2,
+      "level": 2,
+      "Debug": 1,
+      "Error": 1,
+      "no": 9,
+      "colors": 2,
+      "disable": 1,
+      "ANSI": 1,
+      "color": 1,
+      "codes": 1,
+      "create": 2,
+      "start": 1,
+      "even": 1,
+      "current": 1,
+      "directory": 3,
+      "contains": 2,
+      "project": 1,
+      "dir": 3,
+      "<path>": 3,
+      "global": 1,
+      "settings/plugins": 1,
+      "default": 4,
+      "/.sbt/": 1,
+      "<version>": 1,
+      "boot": 3,
+      "shared": 1,
+      "/.sbt/boot": 1,
+      "series": 1,
+      "ivy": 2,
+      "Ivy": 1,
+      "/.ivy2": 1,
+      "<integer>": 1,
+      "memory": 1,
+      "share": 2,
+      "use": 1,
+      "all": 1,
+      "caches": 1,
+      "sharing": 1,
+      "offline": 3,
+      "put": 1,
+      "mode": 2,
+      "jvm": 2,
+      "<port>": 1,
+      "Turn": 1,
+      "on": 2,
+      "JVM": 1,
+      "debugging": 1,
+      "open": 1,
+      "at": 1,
+      "given": 2,
+      "port.": 1,
+      "batch": 2,
+      "Disable": 1,
+      "interactive": 1,
+      "The": 1,
+      "way": 1,
+      "accomplish": 1,
+      "pre": 1,
+      "there": 2,
+      "build.properties": 1,
+      "an": 1,
+      "property": 1,
+      "update": 1,
+      "disk.": 1,
+      "That": 1,
+      "scalacOptions": 3,
+      "S": 2,
+      "stripped": 1,
+      "In": 1,
+      "duplicated": 1,
+      "or": 1,
+      "conflicting": 1,
+      "order": 1,
+      "above": 1,
+      "shows": 1,
+      "precedence": 1,
+      "JAVA_OPTS": 1,
+      "lowest": 1,
+      "command": 1,
+      "line": 1,
+      "highest.": 1,
+      "addJava": 9,
+      "addSbt": 12,
+      "addScalac": 2,
+      "addResidual": 2,
+      "addResolver": 1,
+      "addDebugger": 2,
+      "get_jvm_opts": 2,
+      "process_args": 2,
+      "require_arg": 12,
+      "type": 1,
+      "while": 2,
+      "gt": 1,
+      "shift": 28,
+      "integer": 1,
+      "inc": 1,
+      "port": 1,
+      "snapshot": 1,
+      "launch": 1,
+      "scala": 3,
+      "home": 2,
+      "D*": 1,
+      "J*": 1,
+      "S*": 1,
+      "sbtargs": 3,
+      "IFS": 1,
+      "read": 1,
+      "<\"$sbt_opts_file\">": 1,
+      "process": 1,
+      "combined": 1,
+      "args": 2,
+      "reset": 1,
+      "residuals": 1,
+      "argumentCount=": 1,
+      "we": 1,
+      "were": 1,
+      "any": 1,
+      "opts": 1,
+      "eq": 1,
+      "0": 1,
+      "ThisBuild": 1,
+      "Update": 1,
+      "properties": 1,
+      "disk": 1,
+      "explicit": 1,
+      "gives": 1,
+      "us": 1,
+      "choice": 1,
+      "Detected": 1,
+      "Overriding": 1,
+      "alert": 1,
+      "them": 1,
+      "here": 1,
+      "argumentCount": 1,
+      "./build.sbt": 1,
+      "./project": 1,
+      "pwd": 1,
+      "doesn": 1,
+      "t": 1,
+      "understand": 1,
+      "iflast": 1,
+      "#residual_args": 1,
       "SHEBANG#!sh": 2,
       "SHEBANG#!zsh": 2
     },
@@ -27452,7 +27713,7 @@
     "Scheme": 3478,
     "Scilab": 69,
     "SCSS": 39,
-    "Shell": 500,
+    "Shell": 2008,
     "Standard ML": 243,
     "SuperCollider": 135,
     "Tea": 3,
@@ -27522,7 +27783,7 @@
     "Scheme": 1,
     "Scilab": 3,
     "SCSS": 1,
-    "Shell": 15,
+    "Shell": 16,
     "Standard ML": 2,
     "SuperCollider": 1,
     "Tea": 1,
@@ -27537,5 +27798,5 @@
     "XSLT": 1,
     "YAML": 1
   },
-  "md5": "ca1d189ca79aa9c52370da78f2c2b4dd"
+  "md5": "73937d71c79ba8a2f9e085431017cb2d"
 }

samples/Shell/sbt.script!

@@ -0,0 +1,432 @@
+#!/usr/bin/env bash
+#
+# A more capable sbt runner, coincidentally also called sbt.
+# Author: Paul Phillips <paulp@typesafe.com>
+
+# todo - make this dynamic
+declare -r sbt_release_version=0.11.3
+declare -r sbt_snapshot_version=0.13.0-SNAPSHOT
+
+unset sbt_jar sbt_dir sbt_create sbt_snapshot sbt_launch_dir
+unset scala_version java_home sbt_explicit_version
+unset verbose debug quiet
+
+build_props_sbt () {
+  if [[ -f project/build.properties ]]; then
+    versionLine=$(grep ^sbt.version project/build.properties)
+    versionString=${versionLine##sbt.version=}
+    echo "$versionString"
+  fi
+}
+
+update_build_props_sbt () {
+  local ver="$1"
+  local old=$(build_props_sbt)
+
+  if [[ $ver == $old ]]; then
+    return
+  elif [[ -f project/build.properties ]]; then
+    perl -pi -e "s/^sbt\.version=.*\$/sbt.version=${ver}/" project/build.properties
+    grep -q '^sbt.version=' project/build.properties || echo "sbt.version=${ver}" >> project/build.properties
+
+    echo !!!
+    echo !!! Updated file project/build.properties setting sbt.version to: $ver
+    echo !!! Previous value was: $old
+    echo !!!
+  fi
+}
+
+sbt_version () {
+  if [[ -n $sbt_explicit_version ]]; then
+    echo $sbt_explicit_version
+  else
+    local v=$(build_props_sbt)
+    if [[ -n $v ]]; then
+      echo $v
+    else
+      echo $sbt_release_version
+    fi
+  fi
+}
+
+echoerr () {
+  echo 1>&2 "$@"
+}
+vlog () {
+  [[ $verbose || $debug ]] && echoerr "$@"
+}
+dlog () {
+  [[ $debug ]] && echoerr "$@"
+}
+
+# this seems to cover the bases on OSX, and someone will
+# have to tell me about the others.
+get_script_path () {
+  local path="$1"
+  [[ -L "$path" ]] || { echo "$path" ; return; }
+
+  local target=$(readlink "$path")
+  if [[ "${target:0:1}" == "/" ]]; then
+    echo "$target"
+  else
+    echo "$(dirname $path)/$target"
+  fi
+}
+
+# a ham-fisted attempt to move some memory settings in concert
+# so they need not be dicked around with individually.
+get_mem_opts () {
+  local mem=${1:-1536}
+  local perm=$(( $mem / 4 ))
+  (( $perm > 256 )) || perm=256
+  (( $perm < 1024 )) || perm=1024
+  local codecache=$(( $perm / 2 ))
+  
+  echo "-Xms${mem}m -Xmx${mem}m -XX:MaxPermSize=${perm}m -XX:ReservedCodeCacheSize=${codecache}m"
+}
+
+die() {
+  echo "Aborting: $@"
+  exit 1
+}
+
+make_url () {
+  groupid="$1"
+  category="$2"
+  version="$3"
+  
+  echo "http://typesafe.artifactoryonline.com/typesafe/ivy-$category/$groupid/sbt-launch/$version/sbt-launch.jar"
+}
+
+declare -r default_jvm_opts="-Dfile.encoding=UTF8"
+declare -r default_sbt_opts="-XX:+CMSClassUnloadingEnabled"
+declare -r default_sbt_mem=1536
+declare -r noshare_opts="-Dsbt.global.base=project/.sbtboot -Dsbt.boot.directory=project/.boot -Dsbt.ivy.home=project/.ivy"
+declare -r sbt_opts_file=".sbtopts"
+declare -r jvm_opts_file=".jvmopts"
+declare -r latest_28="2.8.2"
+declare -r latest_29="2.9.1"
+declare -r latest_210="2.10.0-SNAPSHOT"
+
+declare -r script_path=$(get_script_path "$BASH_SOURCE")
+declare -r script_dir="$(dirname $script_path)"
+declare -r script_name="$(basename $script_path)"
+
+# some non-read-onlies set with defaults
+declare java_cmd=java
+declare sbt_launch_dir="$script_dir/.lib"
+declare sbt_mem=$default_sbt_mem
+
+# pull -J and -D options to give to java.
+declare -a residual_args
+declare -a java_args
+declare -a scalac_args
+declare -a sbt_commands
+
+build_props_scala () {
+  if [[ -f project/build.properties ]]; then
+    versionLine=$(grep ^build.scala.versions project/build.properties)
+    versionString=${versionLine##build.scala.versions=}
+    echo ${versionString%% .*}
+  fi
+}
+
+execRunner () {
+  # print the arguments one to a line, quoting any containing spaces
+  [[ $verbose || $debug ]] && echo "# Executing command line:" && {
+    for arg; do
+      if printf "%s\n" "$arg" | grep -q ' '; then
+        printf "\"%s\"\n" "$arg"
+      else
+        printf "%s\n" "$arg"
+      fi
+    done
+    echo ""
+  }
+
+  exec "$@"
+}
+
+sbt_groupid () {
+  case $(sbt_version) in
+        0.7.*) echo org.scala-tools.sbt ;;
+       0.10.*) echo org.scala-tools.sbt ;;
+    0.11.[12]) echo org.scala-tools.sbt ;;
+            *) echo org.scala-sbt ;;
+  esac
+}
+
+sbt_artifactory_list () {
+  local version0=$(sbt_version)
+  local version=${version0%-SNAPSHOT}
+  local url="http://typesafe.artifactoryonline.com/typesafe/ivy-snapshots/$(sbt_groupid)/sbt-launch/"
+  dlog "Looking for snapshot list at: $url "
+  
+  curl -s --list-only "$url" | \
+    grep -F $version | \
+    perl -e 'print reverse <>' | \
+    perl -pe 's#^<a href="([^"/]+).*#$1#;'
+}
+
+make_release_url () {
+  make_url $(sbt_groupid) releases $(sbt_version)
+}
+
+# argument is e.g. 0.13.0-SNAPSHOT
+# finds the actual version (with the build id) at artifactory
+make_snapshot_url () {
+  for ver in $(sbt_artifactory_list); do
+    local url=$(make_url $(sbt_groupid) snapshots $ver)
+    dlog "Testing $url"
+    curl -s --head "$url" >/dev/null
+    dlog "curl returned: $?"
+    echo "$url"
+    return
+  done
+}
+
+jar_url () {
+  case $(sbt_version) in
+             0.7.*) echo "http://simple-build-tool.googlecode.com/files/sbt-launch-0.7.7.jar" ;;
+        *-SNAPSHOT) make_snapshot_url ;;
+                 *) make_release_url ;;
+  esac
+}
+
+jar_file () {
+  echo "$sbt_launch_dir/$1/sbt-launch.jar"
+}
+
+download_url () {
+  local url="$1"
+  local jar="$2"
+  
+  echo "Downloading sbt launcher $(sbt_version):"
+  echo "  From  $url"
+  echo "    To  $jar"
+
+  mkdir -p $(dirname "$jar") && {
+    if which curl >/dev/null; then
+      curl --fail --silent "$url" --output "$jar"
+    elif which wget >/dev/null; then
+      wget --quiet -O "$jar" "$url"
+    fi
+  } && [[ -f "$jar" ]]
+}
+
+acquire_sbt_jar () {
+  sbt_url="$(jar_url)"
+  sbt_jar="$(jar_file $(sbt_version))"
+
+  [[ -f "$sbt_jar" ]] || download_url "$sbt_url" "$sbt_jar"
+}
+
+usage () {
+  cat <<EOM
+Usage: $script_name [options]
+
+  -h | -help         print this message
+  -v | -verbose      this runner is chattier
+  -d | -debug        set sbt log level to Debug
+  -q | -quiet        set sbt log level to Error
+  -no-colors         disable ANSI color codes
+  -sbt-create        start sbt even if current directory contains no sbt project
+  -sbt-dir   <path>  path to global settings/plugins directory (default: ~/.sbt/<version>)
+  -sbt-boot  <path>  path to shared boot directory (default: ~/.sbt/boot in 0.11 series)
+  -ivy       <path>  path to local Ivy repository (default: ~/.ivy2)
+  -mem    <integer>  set memory options (default: $sbt_mem, which is
+                       $(get_mem_opts $sbt_mem) )
+  -no-share          use all local caches; no sharing
+  -offline           put sbt in offline mode
+  -jvm-debug <port>  Turn on JVM debugging, open at the given port.
+  -batch             Disable interactive mode
+
+  # sbt version (default: from project/build.properties if present, else latest release)
+  !!! The only way to accomplish this pre-0.12.0 if there is a build.properties file which
+  !!! contains an sbt.version property is to update the file on disk.  That's what this does.
+  -sbt-version  <version>   use the specified version of sbt 
+  -sbt-jar      <path>      use the specified jar as the sbt launcher
+  -sbt-snapshot             use a snapshot version of sbt
+  -sbt-launch-dir <path>    directory to hold sbt launchers (default: $sbt_launch_dir)
+
+  # scala version (default: as chosen by sbt)
+  -28                       use $latest_28
+  -29                       use $latest_29
+  -210                      use $latest_210
+  -scala-home <path>        use the scala build at the specified directory
+  -scala-version <version>  use the specified version of scala
+
+  # java version (default: java from PATH, currently $(java -version |& grep version))
+  -java-home <path>         alternate JAVA_HOME
+
+  # jvm options and output control
+  JAVA_OPTS     environment variable holding jvm args, if unset uses "$default_jvm_opts"
+  SBT_OPTS      environment variable holding jvm args, if unset uses "$default_sbt_opts"
+  .jvmopts      if file is in sbt root, it is prepended to the args given to the jvm
+  .sbtopts      if file is in sbt root, it is prepended to the args given to **sbt**
+  -Dkey=val     pass -Dkey=val directly to the jvm
+  -J-X          pass option -X directly to the jvm (-J is stripped)
+  -S-X          add -X to sbt's scalacOptions (-S is stripped)
+
+In the case of duplicated or conflicting options, the order above
+shows precedence: JAVA_OPTS lowest, command line options highest.
+EOM
+}
+
+addJava () {
+  dlog "[addJava] arg = '$1'"
+  java_args=( "${java_args[@]}" "$1" )
+}
+addSbt () {
+  dlog "[addSbt] arg = '$1'"
+  sbt_commands=( "${sbt_commands[@]}" "$1" )
+}
+addScalac () {
+  dlog "[addScalac] arg = '$1'"
+  scalac_args=( "${scalac_args[@]}" "$1" )
+}
+addResidual () {
+  dlog "[residual] arg = '$1'"
+  residual_args=( "${residual_args[@]}" "$1" )
+}
+addResolver () {
+  addSbt "set resolvers in ThisBuild += $1"
+}
+addDebugger () {
+  addJava "-Xdebug -Xrunjdwp:transport=dt_socket,server=y,suspend=n,address=$1"
+}
+get_jvm_opts () {
+  # echo "${JAVA_OPTS:-$default_jvm_opts}"
+  # echo "${SBT_OPTS:-$default_sbt_opts}"
+
+  [[ -f "$jvm_opts_file" ]] && cat "$jvm_opts_file"
+}
+
+process_args ()
+{
+  require_arg () {
+    local type="$1"
+    local opt="$2"
+    local arg="$3"
+    
+    if [[ -z "$arg" ]] || [[ "${arg:0:1}" == "-" ]]; then
+      die "$opt requires <$type> argument"
+    fi
+  }
+  while [[ $# -gt 0 ]]; do
+    case "$1" in
+       -h|-help) usage; exit 1 ;;
+    -v|-verbose) verbose=1 && shift ;;
+      -d|-debug) debug=1 && shift ;;
+      -q|-quiet) quiet=1 && shift ;;
+
+           -ivy) require_arg path "$1" "$2" && addJava "-Dsbt.ivy.home=$2" && shift 2 ;;
+           -mem) require_arg integer "$1" "$2" && sbt_mem="$2" && shift 2 ;;
+     -no-colors) addJava "-Dsbt.log.noformat=true" && shift ;;
+      -no-share) addJava "$noshare_opts" && shift ;;
+      -sbt-boot) require_arg path "$1" "$2" && addJava "-Dsbt.boot.directory=$2" && shift 2 ;;
+       -sbt-dir) require_arg path "$1" "$2" && sbt_dir="$2" && shift 2 ;;
+     -debug-inc) addJava "-Dxsbt.inc.debug=true" && shift ;;
+       -offline) addSbt "set offline := true" && shift ;;
+     -jvm-debug) require_arg port "$1" "$2" && addDebugger $2 && shift 2 ;;
+         -batch) exec </dev/null && shift ;;
+
+    -sbt-create) sbt_create=true && shift ;;
+  -sbt-snapshot) sbt_explicit_version=$sbt_snapshot_version && shift ;;
+       -sbt-jar) require_arg path "$1" "$2" && sbt_jar="$2" && shift 2 ;;
+   -sbt-version) require_arg version "$1" "$2" && sbt_explicit_version="$2" && shift 2 ;;
+-sbt-launch-dir) require_arg path "$1" "$2" && sbt_launch_dir="$2" && shift 2 ;;
+ -scala-version) require_arg version "$1" "$2" && addSbt "set scalaVersion := \"$2\"" && shift 2 ;;
+    -scala-home) require_arg path "$1" "$2" && addSbt "set scalaHome in ThisBuild := Some(file(\"$2\"))" && shift 2 ;;
+     -java-home) require_arg path "$1" "$2" && java_cmd="$2/bin/java" && shift 2 ;;
+
+            -D*) addJava "$1" && shift ;;
+            -J*) addJava "${1:2}" && shift ;;
+            -S*) addScalac "${1:2}" && shift ;;
+            -28) addSbt "++ $latest_28" && shift ;;
+            -29) addSbt "++ $latest_29" && shift ;;
+           -210) addSbt "++ $latest_210" && shift ;;
+
+              *) addResidual "$1" && shift ;;
+    esac
+  done
+  
+  [[ $debug ]] && {
+    case $(sbt_version) in
+     0.7.*) addSbt "debug" ;; 
+         *) addSbt "set logLevel in Global := Level.Debug" ;;
+    esac
+  }
+  [[ $quiet ]] && {
+    case $(sbt_version) in
+     0.7.*) ;; 
+         *) addSbt "set logLevel in Global := Level.Error" ;;
+    esac
+  }
+}
+
+# if .sbtopts exists, prepend its contents to $@ so it can be processed by this runner
+[[ -f "$sbt_opts_file" ]] && {
+  sbtargs=()
+  while IFS= read -r arg; do
+    sbtargs=( "${sbtargs[@]}" "$arg" )
+  done <"$sbt_opts_file"
+
+  set -- "${sbtargs[@]}" "$@"
+}
+
+# process the combined args, then reset "$@" to the residuals
+process_args "$@"
+set -- "${residual_args[@]}"
+argumentCount=$#
+
+# set scalacOptions if we were given any -S opts
+[[ ${#scalac_args[@]} -eq 0 ]] || addSbt "set scalacOptions in ThisBuild += \"${scalac_args[@]}\""
+
+# Update build.properties no disk to set explicit version - sbt gives us no choice
+[[ -n "$sbt_explicit_version" ]] && update_build_props_sbt "$sbt_explicit_version"
+echo "Detected sbt version $(sbt_version)"
+
+[[ -n "$scala_version" ]] && echo "Overriding scala version to $scala_version"
+
+# no args - alert them there's stuff in here
+(( $argumentCount > 0 )) || echo "Starting $script_name: invoke with -help for other options"
+
+# verify this is an sbt dir or -create was given
+[[ -f ./build.sbt || -d ./project || -n "$sbt_create" ]] || {
+  cat <<EOM
+$(pwd) doesn't appear to be an sbt project.
+If you want to start sbt anyway, run:
+  $0 -sbt-create
+
+EOM
+  exit 1
+}
+
+# pick up completion if present; todo
+[[ -f .sbt_completion.sh ]] && source .sbt_completion.sh
+
+# no jar? download it.
+[[ -f "$sbt_jar" ]] || acquire_sbt_jar || {
+  # still no jar? uh-oh.
+  echo "Download failed. Obtain the jar manually and place it at $sbt_jar"
+  exit 1
+}
+
+[[ -n "$sbt_dir" ]] || {
+  sbt_dir=~/.sbt/$(sbt_version)
+  addJava "-Dsbt.global.base=$sbt_dir"
+  echo "Using $sbt_dir as sbt dir, -sbt-dir to override."
+}
+
+# since sbt 0.7 doesn't understand iflast
+(( ${#residual_args[@]} == 0 )) && residual_args=( "shell" )
+
+# run sbt
+execRunner "$java_cmd" \
+  $(get_mem_opts $sbt_mem) \
+  $(get_jvm_opts) \
+  ${java_args[@]} \
+  -jar "$sbt_jar" \
+  "${sbt_commands[@]}" \
+  "${residual_args[@]}"

test/test_blob.rb

@@ -2,6 +2,7 @@ require 'linguist/file_blob'
 require 'linguist/samples'
 
 require 'test/unit'
+require 'mocha'
 require 'mime/types'
 require 'pygments'
 
@@ -261,6 +262,12 @@ class TestBlob < Test::Unit::TestCase
     assert !blob("Text/dump.sql").indexable?
     assert !blob("Binary/github.po").indexable?
     assert !blob("Binary/linguist.gem").indexable?
+
+    # large binary blobs should fail on size check first, not call 
+    # into charlock_holmes and alloc big buffers for testing encoding
+    b = blob("Binary/octocat.ai")
+    b.expects(:binary?).never
+    assert !b.indexable?
   end
 
   def test_language