whitespace check: rewrite in Julia, add checks

This now checks for:

- trailing non-ASCII whitespace
- non-breaking spaces anywhere
- non-UNIX line endings
- trailing blank lines
- no trailing newline

Git can't handle this, largely because whether it interprets files as
UTF-8 or Latin-1 depends on how system libraries that it uses for regex
matching are compiled, which is inconsistent and hard to fix. The end of
file checks are also quite awkard and inefficient to implement with Git
and shell scripting. Julia is fast and lets us present results clearly.

Makefile

@@ -99,7 +99,7 @@ docs-revise:
 
 check-whitespace:
 ifneq ($(NO_GIT), 1)
- @$(JULIAHOME)/contrib/check-whitespace.sh
+ @$(JULIAHOME)/contrib/check-whitespace.jl
 else
  $(warn "Skipping whitespace check because git is unavailable")
 endif

contrib/README.md

@@ -6,7 +6,7 @@ Installation
 |[ mac/ ](https://github.com/JuliaLang/julia/blob/master/contrib/mac/) | Mac install files |
 |[ windows/ ](https://github.com/JuliaLang/julia/blob/master/contrib/windows/) | Windows install files |
 |[ add_license_to_files.jl ](https://github.com/JuliaLang/julia/blob/master/contrib/add_license_to_files.jl ) | Add the Julia license to files in the Julia Project |
-|[ check-whitespace.sh ](https://github.com/JuliaLang/julia/blob/master/contrib/check-whitespace.sh) | Check for trailing white space |
+|[ check-whitespace.jl ](https://github.com/JuliaLang/julia/blob/master/contrib/check-whitespace.jl) | Check for white space issues |
 |[ commit-name.sh ](https://github.com/JuliaLang/julia/blob/master/contrib/commit-name.sh) | Computes a version name for a commit |
 |[ fixup-libgfortran.sh ](https://github.com/JuliaLang/julia/blob/master/contrib/fixup-libgfortran.sh) | Include libgfortran and libquadmath for installations |
 |[ fixup-libstdc++.sh ](https://github.com/JuliaLang/julia/blob/master/contrib/fixup-libstdc++.sh) | Include libstdc++ for installations |

contrib/check-whitespace.jl

@@ -0,0 +1,55 @@
+#!/usr/bin/env julia
+
+const patterns = split("""
+ *.1
+ *.c
+ *.cpp
+ *.h
+ *.inc
+ *.jl
+ *.lsp
+ *.make
+ *.md
+ *.mk
+ *.rst
+ *.scm
+ *.sh
+ *.yml
+ *Makefile
+""")
+
+const errors = Set{Tuple{String,Int,String}}()
+
+for path in eachline(`git ls-files -- $patterns`)
+ lineno = 0
+ non_blank = 0
+
+ file_err(msg) = push!(errors, (path, 0, msg))
+ line_err(msg) = push!(errors, (path, lineno, msg))
+
+ for line in eachline(path, keep=true)
+ lineno += 1
+ contains(line, '\r') && file_err("non-UNIX line endings")
+ contains(line, '\ua0') && line_err("non-breaking space")
+ endswith(line, '\n') || line_err("no trailing newline")
+ line = chomp(line)
+ endswith(line, r"\s") && line_err("trailing whitespace")
+ contains(line, r"\S") && (non_blank = lineno)
+ end
+ non_blank < lineno && line_err("trailing blank lines")
+end
+
+if isempty(errors)
+ println(stderr, "Whitespace check found no issues.")
+ exit(0)
+else
+ println(stderr, "Whitespace check found $(length(errors)) issues:")
+ for (path, lineno, msg) in sort!(collect(errors))
+ if lineno == 0
+ println(stderr, "$path -- $msg")
+ else
+ println(stderr, "$path:$lineno -- $msg")
+ end
+ end
+ exit(1)
+end