git/convert.c

#include "cache.h"
#include "config.h"
#include "object-store.h"
#include "attr.h"
#include "run-command.h"
#include "quote.h"
#include "sigchain.h"
#include "pkt-line.h"
#include "sub-process.h"
#include "utf8.h"
#include "ll-merge.h"

/*
 * convert.c - convert a file when checking it out and checking it in.
 *
 * This should use the pathname to decide on whether it wants to do some
 * more interesting conversions (automatic gzip/unzip, general format
 * conversions etc etc), but by default it just does automatic CRLF<->LF
 * translation when the "text" attribute or "auto_crlf" option is set.
 */

/* Stat bits: When BIN is set, the txt bits are unset */
#define CONVERT_STAT_BITS_TXT_LF    0x1
#define CONVERT_STAT_BITS_TXT_CRLF  0x2
#define CONVERT_STAT_BITS_BIN       0x4

struct text_stat {
	/* NUL, CR, LF and CRLF counts */
	unsigned nul, lonecr, lonelf, crlf;

	/* These are just approximations! */
	unsigned printable, nonprintable;
};

static void gather_stats(const char *buf, unsigned long size, struct text_stat *stats)
{
	unsigned long i;

	memset(stats, 0, sizeof(*stats));

	for (i = 0; i < size; i++) {
		unsigned char c = buf[i];
		if (c == '\r') {
			if (i+1 < size && buf[i+1] == '\n') {
				stats->crlf++;
				i++;
			} else
				stats->lonecr++;
			continue;
		}
		if (c == '\n') {
			stats->lonelf++;
			continue;
		}
		if (c == 127)
			/* DEL */
			stats->nonprintable++;
		else if (c < 32) {
			switch (c) {
				/* BS, HT, ESC and FF */
			case '\b': case '\t': case '\033': case '\014':
				stats->printable++;
				break;
			case 0:
				stats->nul++;
				/* fall through */
			default:
				stats->nonprintable++;
			}
		}
		else
			stats->printable++;
	}

	/* If file ends with EOF then don't count this EOF as non-printable. */
	if (size >= 1 && buf[size-1] == '\032')
		stats->nonprintable--;
}

/*
 * The same heuristics as diff.c::mmfile_is_binary()
 * We treat files with bare CR as binary
 */
static int convert_is_binary(const struct text_stat *stats)
{
	if (stats->lonecr)
		return 1;
	if (stats->nul)
		return 1;
	if ((stats->printable >> 7) < stats->nonprintable)
		return 1;
	return 0;
}

static unsigned int gather_convert_stats(const char *data, unsigned long size)
{
	struct text_stat stats;
	int ret = 0;
	if (!data || !size)
		return 0;
	gather_stats(data, size, &stats);
	if (convert_is_binary(&stats))
		ret |= CONVERT_STAT_BITS_BIN;
	if (stats.crlf)
		ret |= CONVERT_STAT_BITS_TXT_CRLF;
	if (stats.lonelf)
		ret |=  CONVERT_STAT_BITS_TXT_LF;

	return ret;
}

static const char *gather_convert_stats_ascii(const char *data, unsigned long size)
{
	unsigned int convert_stats = gather_convert_stats(data, size);

	if (convert_stats & CONVERT_STAT_BITS_BIN)
		return "-text";
	switch (convert_stats) {
	case CONVERT_STAT_BITS_TXT_LF:
		return "lf";
	case CONVERT_STAT_BITS_TXT_CRLF:
		return "crlf";
	case CONVERT_STAT_BITS_TXT_LF | CONVERT_STAT_BITS_TXT_CRLF:
		return "mixed";
	default:
		return "none";
	}
}

const char *get_cached_convert_stats_ascii(struct index_state *istate,
					   const char *path)
{
	const char *ret;
	unsigned long sz;
	void *data = read_blob_data_from_index(istate, path, &sz);
	ret = gather_convert_stats_ascii(data, sz);
	free(data);
	return ret;
}

const char *get_wt_convert_stats_ascii(const char *path)
{
	const char *ret = "";
	struct strbuf sb = STRBUF_INIT;
	if (strbuf_read_file(&sb, path, 0) >= 0)
		ret = gather_convert_stats_ascii(sb.buf, sb.len);
	strbuf_release(&sb);
	return ret;
}

static int text_eol_is_crlf(void)
{
	if (auto_crlf == AUTO_CRLF_TRUE)
		return 1;
	else if (auto_crlf == AUTO_CRLF_INPUT)
		return 0;
	if (core_eol == EOL_CRLF)
		return 1;
	if (core_eol == EOL_UNSET && EOL_NATIVE == EOL_CRLF)
		return 1;
	return 0;
}

static enum eol output_eol(enum convert_crlf_action crlf_action)
{
	switch (crlf_action) {
	case CRLF_BINARY:
		return EOL_UNSET;
	case CRLF_TEXT_CRLF:
		return EOL_CRLF;
	case CRLF_TEXT_INPUT:
		return EOL_LF;
	case CRLF_UNDEFINED:
	case CRLF_AUTO_CRLF:
		return EOL_CRLF;
	case CRLF_AUTO_INPUT:
		return EOL_LF;
	case CRLF_TEXT:
	case CRLF_AUTO:
		/* fall through */
		return text_eol_is_crlf() ? EOL_CRLF : EOL_LF;
	}
	warning(_("illegal crlf_action %d"), (int)crlf_action);
	return core_eol;
}

static void check_global_conv_flags_eol(const char *path,
			    struct text_stat *old_stats, struct text_stat *new_stats,
			    int conv_flags)
{
	if (old_stats->crlf && !new_stats->crlf ) {
		/*
		 * CRLFs would not be restored by checkout
		 */
		if (conv_flags & CONV_EOL_RNDTRP_DIE)
			die(_("CRLF would be replaced by LF in %s"), path);
		else if (conv_flags & CONV_EOL_RNDTRP_WARN)
			warning(_("CRLF will be replaced by LF in %s.\n"
				  "The file will have its original line"
				  " endings in your working directory"), path);
	} else if (old_stats->lonelf && !new_stats->lonelf ) {
		/*
		 * CRLFs would be added by checkout
		 */
		if (conv_flags & CONV_EOL_RNDTRP_DIE)
			die(_("LF would be replaced by CRLF in %s"), path);
		else if (conv_flags & CONV_EOL_RNDTRP_WARN)
			warning(_("LF will be replaced by CRLF in %s.\n"
				  "The file will have its original line"
				  " endings in your working directory"), path);
	}
}

static int has_crlf_in_index(struct index_state *istate, const char *path)
{
	unsigned long sz;
	void *data;
	const char *crp;
	int has_crlf = 0;

	data = read_blob_data_from_index(istate, path, &sz);
	if (!data)
		return 0;

	crp = memchr(data, '\r', sz);
	if (crp) {
		unsigned int ret_stats;
		ret_stats = gather_convert_stats(data, sz);
		if (!(ret_stats & CONVERT_STAT_BITS_BIN) &&
		    (ret_stats & CONVERT_STAT_BITS_TXT_CRLF))
			has_crlf = 1;
	}
	free(data);
	return has_crlf;
}

static int will_convert_lf_to_crlf(struct text_stat *stats,
				   enum convert_crlf_action crlf_action)
{
	if (output_eol(crlf_action) != EOL_CRLF)
		return 0;
	/* No "naked" LF? Nothing to convert, regardless. */
	if (!stats->lonelf)
		return 0;

	if (crlf_action == CRLF_AUTO || crlf_action == CRLF_AUTO_INPUT || crlf_action == CRLF_AUTO_CRLF) {
		/* If we have any CR or CRLF line endings, we do not touch it */
		/* This is the new safer autocrlf-handling */
		if (stats->lonecr || stats->crlf)
			return 0;

		if (convert_is_binary(stats))
			return 0;
	}
	return 1;

}

static int validate_encoding(const char *path, const char *enc,
		      const char *data, size_t len, int die_on_error)
{
	const char *stripped;

	/* We only check for UTF here as UTF?? can be an alias for UTF-?? */
	if (skip_iprefix(enc, "UTF", &stripped)) {
		skip_prefix(stripped, "-", &stripped);

		/*
		 * Check for detectable errors in UTF encodings
		 */
		if (has_prohibited_utf_bom(enc, data, len)) {
			const char *error_msg = _(
				"BOM is prohibited in '%s' if encoded as %s");
			/*
			 * This advice is shown for UTF-??BE and UTF-??LE encodings.
			 * We cut off the last two characters of the encoding name
			 * to generate the encoding name suitable for BOMs.
			 */
			const char *advise_msg = _(
				"The file '%s' contains a byte order "
				"mark (BOM). Please use UTF-%.*s as "
				"working-tree-encoding.");
			int stripped_len = strlen(stripped) - strlen("BE");
			advise(advise_msg, path, stripped_len, stripped);
			if (die_on_error)
				die(error_msg, path, enc);
			else {
				return error(error_msg, path, enc);
			}

		} else if (is_missing_required_utf_bom(enc, data, len)) {
			const char *error_msg = _(
				"BOM is required in '%s' if encoded as %s");
			const char *advise_msg = _(
				"The file '%s' is missing a byte order "
				"mark (BOM). Please use UTF-%sBE or UTF-%sLE "
				"(depending on the byte order) as "
				"working-tree-encoding.");
			advise(advise_msg, path, stripped, stripped);
			if (die_on_error)
				die(error_msg, path, enc);
			else {
				return error(error_msg, path, enc);
			}
		}

	}
	return 0;
}

static void trace_encoding(const char *context, const char *path,
			   const char *encoding, const char *buf, size_t len)
{
	static struct trace_key coe = TRACE_KEY_INIT(WORKING_TREE_ENCODING);
	struct strbuf trace = STRBUF_INIT;
	int i;

	strbuf_addf(&trace, "%s (%s, considered %s):\n", context, path, encoding);
	for (i = 0; i < len && buf; ++i) {
		strbuf_addf(
			&trace, "| \033[2m%2i:\033[0m %2x \033[2m%c\033[0m%c",
			i,
			(unsigned char) buf[i],
			(buf[i] > 32 && buf[i] < 127 ? buf[i] : ' '),
			((i+1) % 8 && (i+1) < len ? ' ' : '\n')
		);
	}
	strbuf_addchars(&trace, '\n', 1);

	trace_strbuf(&coe, &trace);
	strbuf_release(&trace);
}

static int check_roundtrip(const char *enc_name)
{
	/*
	 * check_roundtrip_encoding contains a string of comma and/or
	 * space separated encodings (eg. "UTF-16, ASCII, CP1125").
	 * Search for the given encoding in that string.
	 */
	const char *found = strcasestr(check_roundtrip_encoding, enc_name);
	const char *next;
	int len;
	if (!found)
		return 0;
	next = found + strlen(enc_name);
	len = strlen(check_roundtrip_encoding);
	return (found && (
			/*
			 * check that the found encoding is at the
			 * beginning of check_roundtrip_encoding or
			 * that it is prefixed with a space or comma
			 */
			found == check_roundtrip_encoding || (
				(isspace(found[-1]) || found[-1] == ',')
			)
		) && (
			/*
			 * check that the found encoding is at the
			 * end of check_roundtrip_encoding or
			 * that it is suffixed with a space or comma
			 */
			next == check_roundtrip_encoding + len || (
				next < check_roundtrip_encoding + len &&
				(isspace(next[0]) || next[0] == ',')
			)
		));
}

static const char *default_encoding = "UTF-8";

static int encode_to_git(const char *path, const char *src, size_t src_len,
			 struct strbuf *buf, const char *enc, int conv_flags)
{
	char *dst;
	size_t dst_len;
	int die_on_error = conv_flags & CONV_WRITE_OBJECT;

	/*
	 * No encoding is specified or there is nothing to encode.
	 * Tell the caller that the content was not modified.
	 */
	if (!enc || (src && !src_len))
		return 0;

	/*
	 * Looks like we got called from "would_convert_to_git()".
	 * This means Git wants to know if it would encode (= modify!)
	 * the content. Let's answer with "yes", since an encoding was
	 * specified.
	 */
	if (!buf && !src)
		return 1;

	if (validate_encoding(path, enc, src, src_len, die_on_error))
		return 0;

	trace_encoding("source", path, enc, src, src_len);
	dst = reencode_string_len(src, src_len, default_encoding, enc,
				  &dst_len);
	if (!dst) {
		/*
		 * We could add the blob "as-is" to Git. However, on checkout
		 * we would try to re-encode to the original encoding. This
		 * would fail and we would leave the user with a messed-up
		 * working tree. Let's try to avoid this by screaming loud.
		 */
		const char* msg = _("failed to encode '%s' from %s to %s");
		if (die_on_error)
			die(msg, path, enc, default_encoding);
		else {
			error(msg, path, enc, default_encoding);
			return 0;
		}
	}
	trace_encoding("destination", path, default_encoding, dst, dst_len);

	/*
	 * UTF supports lossless conversion round tripping [1] and conversions
	 * between UTF and other encodings are mostly round trip safe as
	 * Unicode aims to be a superset of all other character encodings.
	 * However, certain encodings (e.g. SHIFT-JIS) are known to have round
	 * trip issues [2]. Check the round trip conversion for all encodings
	 * listed in core.checkRoundtripEncoding.
	 *
	 * The round trip check is only performed if content is written to Git.
	 * This ensures that no information is lost during conversion to/from
	 * the internal UTF-8 representation.
	 *
	 * Please note, the code below is not tested because I was not able to
	 * generate a faulty round trip without an iconv error. Iconv errors
	 * are already caught above.
	 *
	 * [1] http://unicode.org/faq/utf_bom.html#gen2
	 * [2] https://support.microsoft.com/en-us/help/170559/prb-conversion-problem-between-shift-jis-and-unicode
	 */
	if (die_on_error && check_roundtrip(enc)) {
		char *re_src;
		size_t re_src_len;

		re_src = reencode_string_len(dst, dst_len,
					     enc, default_encoding,
					     &re_src_len);

		trace_printf("Checking roundtrip encoding for %s...\n", enc);
		trace_encoding("reencoded source", path, enc,
			       re_src, re_src_len);

		if (!re_src || src_len != re_src_len ||
		    memcmp(src, re_src, src_len)) {
			const char* msg = _("encoding '%s' from %s to %s and "
					    "back is not the same");
			die(msg, path, enc, default_encoding);
		}

		free(re_src);
	}

	strbuf_attach(buf, dst, dst_len, dst_len + 1);
	return 1;
}

static int encode_to_worktree(const char *path, const char *src, size_t src_len,
			      struct strbuf *buf, const char *enc)
{
	char *dst;
	size_t dst_len;

	/*
	 * No encoding is specified or there is nothing to encode.
	 * Tell the caller that the content was not modified.
	 */
	if (!enc || (src && !src_len))
		return 0;

	dst = reencode_string_len(src, src_len, enc, default_encoding,
				  &dst_len);
	if (!dst) {
		error(_("failed to encode '%s' from %s to %s"),
		      path, default_encoding, enc);
		return 0;
	}

	strbuf_attach(buf, dst, dst_len, dst_len + 1);
	return 1;
}

static int crlf_to_git(struct index_state *istate,
		       const char *path, const char *src, size_t len,
		       struct strbuf *buf,
		       enum convert_crlf_action crlf_action, int conv_flags)
{
	struct text_stat stats;
	char *dst;
	int convert_crlf_into_lf;

	if (crlf_action == CRLF_BINARY ||
	    (src && !len))
		return 0;

	/*
	 * If we are doing a dry-run and have no source buffer, there is
	 * nothing to analyze; we must assume we would convert.
	 */
	if (!buf && !src)
		return 1;

	gather_stats(src, len, &stats);
	/* Optimization: No CRLF? Nothing to convert, regardless. */
	convert_crlf_into_lf = !!stats.crlf;

	if (crlf_action == CRLF_AUTO || crlf_action == CRLF_AUTO_INPUT || crlf_action == CRLF_AUTO_CRLF) {
		if (convert_is_binary(&stats))
			return 0;
		/*
		 * If the file in the index has any CR in it, do not
		 * convert.  This is the new safer autocrlf handling,
		 * unless we want to renormalize in a merge or
		 * cherry-pick.
		 */
		if ((!(conv_flags & CONV_EOL_RENORMALIZE)) &&
		    has_crlf_in_index(istate, path))
			convert_crlf_into_lf = 0;
	}
	if (((conv_flags & CONV_EOL_RNDTRP_WARN) ||
	     ((conv_flags & CONV_EOL_RNDTRP_DIE) && len))) {