From 6918357031df3a7e3373fcb0b28657ead4afc1bb Mon Sep 17 00:00:00 2001
From: Marcel van Lohuizen <mpvl@golang.org>
Date: Mon, 20 Aug 2012 10:55:40 +0200
Subject: [PATCH] exp/locale/collate: Added test flag to maketables tool for
 comparing newly against previously generated tables.

R=r
CC=golang-dev
https://golang.org/cl/6441098
---
 src/pkg/exp/locale/collate/maketables.go | 89 ++++++++++++++++++++----
 1 file changed, 77 insertions(+), 12 deletions(-)

diff --git a/src/pkg/exp/locale/collate/maketables.go b/src/pkg/exp/locale/collate/maketables.go
index a76e2d0f93..a42ce9b67b 100644
--- a/src/pkg/exp/locale/collate/maketables.go
+++ b/src/pkg/exp/locale/collate/maketables.go
@@ -11,6 +11,7 @@ package main
 
 import (
 	"bufio"
+	"bytes"
 	"exp/locale/collate"
 	"exp/locale/collate/build"
 	"flag"
@@ -21,6 +22,7 @@ import (
 	"os"
 	"path"
 	"regexp"
+	"sort"
 	"strconv"
 	"strings"
 	"unicode"
@@ -29,6 +31,9 @@ import (
 var ducet = flag.String("ducet",
 	"http://unicode.org/Public/UCA/"+unicode.Version+"/allkeys.txt",
 	"URL of the Default Unicode Collation Element Table (DUCET).")
+var test = flag.Bool("test",
+	false,
+	"test existing tables; can be used to compare web data with package data")
 var localFiles = flag.Bool("local",
 	false,
 	"data files have been copied to the current directory; for debugging only")
@@ -124,6 +129,9 @@ func parseUCA(builder *build.Builder) {
 			if len(part[1]) < n+3 || part[1][n+1] != '#' {
 				log.Fatalf("%d: expected comment; found %s", i, part[1][n:])
 			}
+			if *test {
+				testInput.add(string(lhs))
+			}
 			failOnError(builder.Add(lhs, rhs, vars))
 		}
 	}
@@ -137,6 +145,59 @@ func convHex(line int, s string) int {
 	return int(r)
 }
 
+var testInput = stringSet{}
+
+type stringSet struct {
+	set []string
+}
+
+func (ss *stringSet) add(s string) {
+	ss.set = append(ss.set, s)
+}
+
+func (ss *stringSet) values() []string {
+	ss.compact()
+	return ss.set
+}
+
+func (ss *stringSet) compact() {
+	a := ss.set
+	sort.Strings(a)
+	k := 0
+	for i := 1; i < len(a); i++ {
+		if a[k] != a[i] {
+			a[k+1] = a[i]
+			k++
+		}
+	}
+	ss.set = a[:k+1]
+}
+
+func testCollator(c *collate.Collator) {
+	c0 := collate.Root
+
+	// iterator over all characters for all locales and check
+	// whether Key is equal.
+	buf := collate.Buffer{}
+
+	// Add all common and not too uncommon runes to the test set.
+	for i := rune(0); i < 0x30000; i++ {
+		testInput.add(string(i))
+	}
+	for i := rune(0xE0000); i < 0xF0000; i++ {
+		testInput.add(string(i))
+	}
+	for _, str := range testInput.values() {
+		k0 := c0.KeyFromString(&buf, str)
+		k := c.KeyFromString(&buf, str)
+		if bytes.Compare(k0, k) != 0 {
+			failOnError(fmt.Errorf("test:%U: keys differ (%x vs %x)", []rune(str), k0, k))
+		}
+		buf.ResetKeys()
+	}
+	fmt.Println("PASS")
+}
+
 // TODO: move this functionality to exp/locale/collate/build.
 func printCollators(c *collate.Collator) {
 	const name = "Root"
@@ -157,18 +218,22 @@ func main() {
 	c, err := b.Build()
 	failOnError(err)
 
-	fmt.Println("// Generated by running")
-	fmt.Printf("//  maketables --ducet=%s\n", *ducet)
-	fmt.Println("// DO NOT EDIT")
-	fmt.Println("// TODO: implement more compact representation for sparse blocks.")
-	fmt.Println("")
-	fmt.Println("package collate")
-	fmt.Println("")
-	fmt.Println(`import "exp/norm"`)
-	fmt.Println("")
+	if *test {
+		testCollator(c)
+	} else {
+		fmt.Println("// Generated by running")
+		fmt.Printf("//  maketables --ducet=%s\n", *ducet)
+		fmt.Println("// DO NOT EDIT")
+		fmt.Println("// TODO: implement more compact representation for sparse blocks.")
+		fmt.Println("")
+		fmt.Println("package collate")
+		fmt.Println("")
+		fmt.Println(`import "exp/norm"`)
+		fmt.Println("")
 
-	printCollators(c)
+		printCollators(c)
 
-	_, err = b.Print(os.Stdout)
-	failOnError(err)
+		_, err = b.Print(os.Stdout)
+		failOnError(err)
+	}
 }