Use multiple read format fields to specify non-consecutive sequence. Fix several bugs in parsing. (34905b18) · Commits · github_fork / Chromap

README.md

+2 −2

Original line number	Diff line number	Diff line
		@@ -152,8 +152,8 @@ Chromap also supports user-defined barcode format, including mixed barcode and g
		data case. User can specify the sequence structure through option --read-format. The value
		is a comma-separated string, each field in the string is also a semi-comma-splitted string

		[r1\|r2\|bc]:start0/start1/...:end0/end1/...:strand
		The start and end are inclusive and -1 means the end of the read. User may use '/' symbol to specify multiple segments. The strand is presented by '+' and '-' symbol, if '-' the barcode will be reverse-complemented after extraction. The strand symbol can be omitted if it is '+' and is ignored on r1 and r2. For example,
		[r1\|r2\|bc]:start:end:strand
		The start and end are inclusive and -1 means the end of the read. User may use multiple fields to specify non-consecutive segments, e.g. bc:0:15,bc:32:-1. The strand is presented by '+' and '-' symbol, if '-' the barcode will be reverse-complemented after extraction. The strand symbol can be omitted if it is '+' and is ignored on r1 and r2. For example,
		when the barcode is in the first 16bp of read1, one can use the option
		`-1 read1.fq.gz -2 read2.fq.gz --barcode read1.fq.gz --read-format bc:0:15,r1:16:-1`

+2 −3

Original line number	Diff line number	Diff line
		@@ -720,9 +720,8 @@ void Chromap::ParseReadFormat(const std::string &read_format) {

		uint32_t i, j;
		for (i = 0; i < read_format.size();) {
		for (j = i + 1; j < read_format.size() && j != ','; ++j)
		for (j = i + 1; j < read_format.size() && read_format[j] != ','; ++j)
		;

		bool parse_success = true;
		if (read_format[i] == 'r' && read_format[i + 1] == '1') {
		parse_success = read1_effective_range_.ParseEffectiveRange(
		@@ -741,7 +740,7 @@ void Chromap::ParseReadFormat(const std::string &read_format) {
		ExitWithMessage("Unknown read format: " + read_format + "\n");
		}

		i = j;
		i = j + 1;
		}
		}

+11 −6

Original line number	Diff line number	Diff line
		@@ -22,6 +22,7 @@ class SequenceEffectiveRange {
		ends.push_back(-1);
		strand = 1;
		range_num = 1;
		default_range = true;
		}

		// Return false if it fails to parse the format string.
		@@ -30,14 +31,17 @@ class SequenceEffectiveRange {
		int j = 0; // start, end, strand section
		char buffer[20];
		int blen = 0;

		if (default_range) {
		starts.clear();
		ends.clear();
		strand = 1;
		default_range = false;
		}

		for (i = 3; i <= len; ++i) {
		if (i == len \|\| s[i] == '/' \|\| s[i] == ':') {
		if (i == len \|\| s[i] == ':') {
		buffer[blen] = '\0';

		if (j == 0) {
		starts.push_back(atoi(buffer));
		} else if (j == 1) {
		@@ -121,6 +125,7 @@ class SequenceEffectiveRange {
		std::vector<int> ends;
		int range_num;
		int strand;
		bool default_range; // whether the range has been modified by new input
		};

		} // namespace chromap