Prepare git-tools for merging into the main git archive

Rename into a "tools" subdirectory, and change name of "dotest" to "applymbox".

Remove stripspace (which was already copied into git) and cvs2git (which
was likewise already copied into git, and then replaced by a much better
perl version).

All of this was brought on by Ryan Anderson shaming me into it.  Thanks.
I guess.

5 files changed, 527 insertions, 0 deletions

diff --git a/tools/Makefile b/tools/Makefile
new file mode 100644
index 0000000000..8e7252e592
--- /dev/null
+++ b/tools/Makefile
@@ -0,0 +1,14 @@
+CC=gcc
+CFLAGS=-Wall -O2
+HOME=$(shell echo $$HOME)
+
+PROGRAMS=mailsplit mailinfo
+SCRIPTS=applymbox applypatch
+
+all: $(PROGRAMS)
+
+install: $(PROGRAMS) $(SCRIPTS)
+	cp -f $(PROGRAMS) $(SCRIPTS) $(HOME)/bin/
+
+clean:
+	rm -f $(PROGRAMS) *.o
diff --git a/tools/applymbox b/tools/applymbox
new file mode 100755
index 0000000000..5ac8d2b4da
--- /dev/null
+++ b/tools/applymbox
@@ -0,0 +1,35 @@
+#!/bin/sh
+##
+## "dotest" is my stupid name for my patch-application script, which
+## I never got around to renaming after I tested it. We're now on the
+## second generation of scripts, still called "dotest".
+##
+## Update: Ryan Anderson finally shamed me into naming this "applymbox".
+##
+## You give it a mbox-format collection of emails, and it will try to
+## apply them to the kernel using "applypatch"
+##
+## dotest [ -q ] mail_archive [Signoff_file]
+##
+rm -rf .dotest
+mkdir .dotest
+case $1 in
+
+	-q)	touch .dotest/.query_apply
+		shift;;
+esac
+mailsplit $1 .dotest || exit 1
+for i in .dotest/*
+do
+	mailinfo .dotest/msg .dotest/patch < $i > .dotest/info || exit 1
+	git-stripspace < .dotest/msg > .dotest/msg-clean
+	applypatch .dotest/msg-clean .dotest/patch .dotest/info "$2"
+	ret=$?
+	if [ $ret -ne 0 ]; then
+		# 2 is a special exit code from applypatch to indicate that
+	    	# the patch wasn't applied, but continue anyway 
+		[ $ret -ne 2 ] && exit $ret
+	fi
+done
+# return to pristine
+rm -fr .dotest
diff --git a/tools/applypatch b/tools/applypatch
new file mode 100755
index 0000000000..5a3a44b0e6
--- /dev/null
+++ b/tools/applypatch
@@ -0,0 +1,64 @@
+#!/bin/sh
+##
+## applypatch takes four file arguments, and uses those to
+## apply the unpacked patch (surprise surprise) that they
+## represent to the current tree.
+##
+## The arguments are:
+##	$1 - file with commit message
+##	$2 - file with the actual patch
+##	$3 - "info" file with Author, email and subject
+##	$4 - optional file containing signoff to add
+##
+signoff="$4"
+final=.dotest/final-commit
+##
+## If this file exists, we ask before applying
+##
+query_apply=.dotest/.query_apply
+MSGFILE=$1
+PATCHFILE=$2
+INFO=$3
+EDIT=${VISUAL:-$EDITOR}
+EDIT=${EDIT:-vi}
+
+export GIT_AUTHOR_NAME="$(sed -n '/^Author/ s/Author: //p' .dotest/info)"
+export GIT_AUTHOR_EMAIL="$(sed -n '/^Email/ s/Email: //p' .dotest/info)"
+export GIT_AUTHOR_DATE="$(sed -n '/^Date/ s/Date: //p' .dotest/info)"
+export SUBJECT="$(sed -n '/^Subject/ s/Subject: //p' .dotest/info)"
+
+if [ -n "$signoff" -a -f "$signoff" ]; then
+	cat $signoff >> $MSGFILE
+fi
+
+(echo "[PATCH] $SUBJECT" ; if [ -s $MSGFILE ]; then echo ; cat $MSGFILE; fi ) > $final
+
+f=0
+[ -f $query_apply ] || f=1
+
+while [ $f -eq 0 ]; do
+	echo "Commit Body is:"
+	echo "--------------------------"
+	cat $final
+	echo "--------------------------"
+	echo -n "Apply? [y]es/[n]o/[e]dit/[a]ccept all "
+	read reply
+	case $reply in
+		y|Y) f=1;;
+		n|N) exit 2;;	# special value to tell dotest to keep going
+		e|E) $EDIT $final;;
+		a|A) rm -f $query_apply
+		     f=1;;
+	esac
+done
+
+echo
+echo Applying "'$SUBJECT'"
+echo
+
+git-apply --index $PATCHFILE || exit 1
+tree=$(git-write-tree) || exit 1
+echo Wrote tree $tree
+commit=$(git-commit-tree $tree -p $(cat .git/HEAD) < $final) || exit 1
+echo Committed: $commit
+echo $commit > .git/HEAD
diff --git a/tools/mailinfo.c b/tools/mailinfo.c
new file mode 100644
index 0000000000..ae279bffa5
--- /dev/null
+++ b/tools/mailinfo.c
@@ -0,0 +1,270 @@
+/*
+ * Another stupid program, this one parsing the headers of an
+ * email to figure out authorship and subject
+ */
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <ctype.h>
+
+static FILE *cmitmsg, *patchfile;
+
+static char line[1000];
+static char date[1000];
+static char name[1000];
+static char email[1000];
+static char subject[1000];
+
+static char *sanity_check(char *name, char *email)
+{
+	int len = strlen(name);
+	if (len < 3 || len > 60)
+		return email;
+	if (strchr(name, '@') || strchr(name, '<') || strchr(name, '>'))
+		return email;
+	return name;
+}
+
+static int handle_from(char *line)
+{
+	char *at = strchr(line, '@');
+	char *dst;
+
+	if (!at)
+		return 0;
+
+	/*
+	 * If we already have one email, don't take any confusing lines
+	 */
+	if (*email && strchr(at+1, '@'))
+		return 0;
+
+	while (at > line) {
+		char c = at[-1];
+		if (isspace(c) || c == '<')
+			break;
+		at--;
+	}
+	dst = email;
+	for (;;) {
+		unsigned char c = *at;
+		if (!c || c == '>' || isspace(c))
+			break;
+		*at++ = ' ';
+		*dst++ = c;
+	}
+	*dst++ = 0;
+
+	at = line + strlen(line);
+	while (at > line) {
+		unsigned char c = *--at;
+		if (isalnum(c))
+			break;
+		*at = 0;
+	}
+
+	at = line;
+	for (;;) {
+		unsigned char c = *at;
+		if (!c)
+			break;
+		if (isalnum(c))
+			break;
+		at++;
+	}
+
+	at = sanity_check(at, email);
+	
+	strcpy(name, at);
+	return 1;
+}
+
+static void handle_date(char *line)
+{
+	strcpy(date, line);
+}
+
+static void handle_subject(char *line)
+{
+	strcpy(subject, line);
+}
+
+static void add_subject_line(char *line)
+{
+	while (isspace(*line))
+		line++;
+	*--line = ' ';
+	strcat(subject, line);
+}
+
+static void check_line(char *line, int len)
+{
+	static int cont = -1;
+	if (!memcmp(line, "From:", 5) && isspace(line[5])) {
+		handle_from(line+6);
+		cont = 0;
+		return;
+	}
+	if (!memcmp(line, "Date:", 5) && isspace(line[5])) {
+		handle_date(line+6);
+		cont = 0;
+		return;
+	}
+	if (!memcmp(line, "Subject:", 8) && isspace(line[8])) {
+		handle_subject(line+9);
+		cont = 1;
+		return;
+	}
+	if (isspace(*line)) {
+		switch (cont) {
+		case 0:
+			fprintf(stderr, "I don't do 'Date:' or 'From:' line continuations\n");
+			break;
+		case 1:
+			add_subject_line(line);
+			return;
+		default:
+			break;
+		}
+	}
+	cont = -1;
+}
+
+static char * cleanup_subject(char *subject)
+{
+	for (;;) {
+		char *p;
+		int len, remove;
+		switch (*subject) {
+		case 'r': case 'R':
+			if (!memcmp("e:", subject+1, 2)) {
+				subject +=3;
+				continue;
+			}
+			break;
+		case ' ': case '\t': case ':':
+			subject++;
+			continue;
+
+		case '[':
+			p = strchr(subject, ']');
+			if (!p) {
+				subject++;
+				continue;
+			}
+			len = strlen(p);
+			remove = p - subject;
+			if (remove <= len *2) {
+				subject = p+1;
+				continue;
+			}	
+			break;
+		}
+		return subject;
+	}
+}			
+
+static void cleanup_space(char *buf)
+{
+	unsigned char c;
+	while ((c = *buf) != 0) {
+		buf++;
+		if (isspace(c)) {
+			buf[-1] = ' ';
+			c = *buf;
+			while (isspace(c)) {
+				int len = strlen(buf);
+				memmove(buf, buf+1, len);
+				c = *buf;
+			}
+		}
+	}
+}
+
+static void handle_rest(void)
+{
+	char *sub = cleanup_subject(subject);
+	cleanup_space(name);
+	cleanup_space(date);
+	cleanup_space(email);
+	cleanup_space(sub);
+	printf("Author: %s\nEmail: %s\nSubject: %s\nDate: %s\n\n", name, email, sub, date);
+	FILE *out = cmitmsg;
+
+	do {
+		if (!memcmp("diff -", line, 6) ||
+		    !memcmp("---", line, 3) ||
+		    !memcmp("Index: ", line, 7))
+			out = patchfile;
+
+		fputs(line, out);
+	} while (fgets(line, sizeof(line), stdin) != NULL);
+
+	if (out == cmitmsg) {
+		fprintf(stderr, "No patch found\n");
+		exit(1);
+	}
+
+	fclose(cmitmsg);
+	fclose(patchfile);
+}
+
+static int eatspace(char *line)
+{
+	int len = strlen(line);
+	while (len > 0 && isspace(line[len-1]))
+		line[--len] = 0;
+	return len;
+}
+
+static void handle_body(void)
+{
+	int has_from = 0;
+
+	/* First line of body can be a From: */
+	while (fgets(line, sizeof(line), stdin) != NULL) {
+		int len = eatspace(line);
+		if (!len)
+			continue;
+		if (!memcmp("From:", line, 5) && isspace(line[5])) {
+			if (!has_from && handle_from(line+6)) {
+				has_from = 1;
+				continue;
+			}
+		}
+		line[len] = '\n';
+		handle_rest();
+		break;
+	}
+}
+
+static void usage(void)
+{
+	fprintf(stderr, "mailinfo msg-file path-file < email\n");
+	exit(1);
+}
+
+int main(int argc, char ** argv)
+{
+	if (argc != 3)
+		usage();
+	cmitmsg = fopen(argv[1], "w");
+	if (!cmitmsg) {
+		perror(argv[1]);
+		exit(1);
+	}
+	patchfile = fopen(argv[2], "w");
+	if (!patchfile) {
+		perror(argv[2]);
+		exit(1);
+	}
+	while (fgets(line, sizeof(line), stdin) != NULL) {
+		int len = eatspace(line);
+		if (!len) {
+			handle_body();
+			break;
+		}
+		check_line(line, len);
+	}
+	return 0;
+}
diff --git a/tools/mailsplit.c b/tools/mailsplit.c
new file mode 100644
index 0000000000..9379fbc5e8
--- /dev/null
+++ b/tools/mailsplit.c
@@ -0,0 +1,144 @@
+/*
+ * Totally braindamaged mbox splitter program.
+ *
+ * It just splits a mbox into a list of files: "0001" "0002" ..
+ * so you can process them further from there.
+ */
+#include <unistd.h>
+#include <stdlib.h>
+#include <fcntl.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <sys/mman.h>
+#include <string.h>
+#include <stdio.h>
+#include <ctype.h>
+#include <assert.h>
+
+static int usage(void)
+{
+	fprintf(stderr, "mailsplit <mbox> <directory>\n");
+	exit(1);
+}
+
+static int linelen(const char *map, unsigned long size)
+{
+	int len = 0, c;
+
+	do {
+		c = *map;
+		map++;
+		size--;
+		len++;
+	} while (size && c != '\n');
+	return len;
+}
+
+static int is_from_line(const char *line, int len)
+{
+	const char *colon;
+
+	if (len < 20 || memcmp("From ", line, 5))
+		return 0;
+
+	colon = line + len - 2;
+	line += 5;
+	for (;;) {
+		if (colon < line)
+			return 0;
+		if (*--colon == ':')
+			break;
+	}
+
+	if (!isdigit(colon[-4]) ||
+	    !isdigit(colon[-2]) ||
+	    !isdigit(colon[-1]) ||
+	    !isdigit(colon[ 1]) ||
+	    !isdigit(colon[ 2]))
+		return 0;
+
+	/* year */
+	if (strtol(colon+3, NULL, 10) <= 90)
+		return 0;
+
+	/* Ok, close enough */
+	return 1;
+}
+
+static int parse_email(const void *map, unsigned long size)
+{
+	unsigned long offset;
+
+	if (size < 6 || memcmp("From ", map, 5))
+		goto corrupt;
+
+	/* Make sure we don't trigger on this first line */
+	map++; size--; offset=1;
+
+	/*
+	 * Search for a line beginning with "From ", and 
+	 * having smething that looks like a date format.
+	 */
+	do {
+		int len = linelen(map, size);
+		if (is_from_line(map, len))
+			return offset;
+		map += len;
+		size -= len;
+		offset += len;
+	} while (size);
+	return offset;
+
+corrupt:
+	fprintf(stderr, "corrupt mailbox\n");
+	exit(1);
+}
+
+int main(int argc, char **argv)
+{
+	int fd, nr;
+	struct stat st;
+	unsigned long size;
+	void *map;
+
+	if (argc != 3)
+		usage();
+	fd = open(argv[1], O_RDONLY);
+	if (fd < 0) {
+		perror(argv[1]);
+		exit(1);
+	}
+	if (chdir(argv[2]) < 0)
+		usage();
+	if (fstat(fd, &st) < 0) {
+		perror("stat");
+		exit(1);
+	}
+	size = st.st_size;
+	map = mmap(NULL, size, PROT_READ, MAP_PRIVATE, fd, 0);
+	if (-1 == (int)(long)map) {
+		perror("mmap");
+		exit(1);
+	}
+	close(fd);
+	nr = 0;
+	do {
+		char name[10];
+		unsigned long len = parse_email(map, size);
+		assert(len <= size);
+		sprintf(name, "%04d", ++nr);
+		fd = open(name, O_WRONLY | O_CREAT | O_EXCL, 0600);
+		if (fd < 0) {
+			perror(name);
+			exit(1);
+		}
+		if (write(fd, map, len) != len) {
+			perror("write");
+			exit(1);
+		}
+		close(fd);
+		map += len;
+		size -= len;
+	} while (size > 0);
+	return 0;
+}