Description: Fix spelling errors in various generated binaries Author: Lance Lin Date: 2023-08-29 --- stacks.orig/src/kmer_filter.cc +++ stacks/src/kmer_filter.cc @@ -1011,7 +1011,7 @@ parse_tsv(line, parts); if (parts.size() != 2) { - cerr << "kmer frequencies are not formated correctly: expecting two, tab separated columns, found " << parts.size() << ".\n"; + cerr << "kmer frequencies are not formatted correctly: expecting two, tab separated columns, found " << parts.size() << ".\n"; exit(1); } @@ -1508,7 +1508,7 @@ return 0; } - cerr << "Outputing details to log: '" << log_path << "'\n\n"; + cerr << "Outputting details to log: '" << log_path << "'\n\n"; log << "File\t" << "Retained Reads\t" @@ -1816,14 +1816,14 @@ << " o: path to output the processed files.\n" << " y: output type, either 'fastq' or 'fasta' (default fastq).\n" << " D: capture discarded reads to a file.\n" - << " h: display this help messsage.\n\n" + << " h: display this help message.\n\n" << " Filtering options:\n" << " --rare: turn on filtering based on rare k-mers.\n" << " --abundant: turn on filtering based on abundant k-mers.\n" << " --k-len : specify k-mer size (default 15).\n\n" << " Advanced filtering options:\n" << " --max-k-freq : specify the number of times a kmer must occur to be considered abundant (default 20,000).\n" - << " --min-lim : specify number of rare kmers occuring in a row required to discard a read (default 80% of the k-mer length).\n" + << " --min-lim : specify number of rare kmers occurring in a row required to discard a read (default 80% of the k-mer length).\n" << " --max-lim : specify number of abundant kmers required to discard a read (default 80% of the k-mers in a read).\n\n" << " Normalize data:\n" << " --normalize : normalize read depth according to k-mer coverage.\n\n" --- stacks.orig/src/process_shortreads.cc +++ stacks/src/process_shortreads.cc @@ -684,7 +684,7 @@ return 0; } - cerr << "Outputing details to log: '" << log_path << "'\n\n"; + cerr << "Outputting details to log: '" << log_path << "'\n\n"; init_log(log, argc, argv); @@ -1146,7 +1146,7 @@ << " D: capture discarded reads to a file.\n" << " w: set the size of the sliding window as a fraction of the read length, between 0 and 1 (default 0.15).\n" << " s: set the score limit. If the average score within the sliding window drops below this value, the read is discarded (default 10).\n" - << " h: display this help messsage.\n\n" + << " h: display this help message.\n\n" << " Barcode options:\n" << " --inline-null: barcode is inline with sequence, occurs only on single-end read (default).\n" << " --index-null: barcode is provded in FASTQ header (Illumina i5 or i7 read).\n" --- stacks.orig/src/sstacks.cc +++ stacks/src/sstacks.cc @@ -1247,7 +1247,7 @@ uint match_depth; stringstream sstr; - cerr << "Outputing to file " << out_file << "\n"; + cerr << "Outputting to file " << out_file << "\n"; for (i = sample.begin(); i != sample.end(); i++) { qloc = i->second; --- stacks.orig/src/clone_filter.cc +++ stacks/src/clone_filter.cc @@ -1328,7 +1328,7 @@ << " o: path to output the processed files.\n" << " y: output type, either 'fastq', 'fasta', 'gzfasta', or 'gzfastq' (default same as input type).\n" << " D: capture discarded reads to a file.\n" - << " h: display this help messsage.\n" + << " h: display this help message.\n" << " --oligo-len-1 len: length of the single-end oligo sequence in data set.\n" << " --oligo-len-2 len: length of the paired-end oligo sequence in data set.\n" << " --retain-oligo: do not trim off the random oligo sequence (if oligo is inline).\n\n" --- stacks.orig/src/phasedstacks.cc +++ stacks/src/phasedstacks.cc @@ -1738,14 +1738,14 @@ parse_tsv(line, parts); if (parts.size() != 2) { - cerr << "Population map is not formated correctly: expecting two, tab separated columns, found " << parts.size() << ".\n"; + cerr << "Population map is not formatted correctly: expecting two, tab separated columns, found " << parts.size() << ".\n"; return 0; } strncpy(pop_id_str, parts[1].c_str(), id_len); for (int i = 0; i < id_len && pop_id_str[i] != '\0'; i++) if (!isdigit(pop_id_str[i])) { - cerr << "Population map is not formated correctly: expecting numerical ID in second column, found '" << parts[1] << "'.\n"; + cerr << "Population map is not formatted correctly: expecting numerical ID in second column, found '" << parts[1] << "'.\n"; return 0; } @@ -1953,7 +1953,7 @@ << " p: number of processes to run in parallel sections of code.\n" << " M: path to the population map, a tab separated file describing which individuals belong in which population.\n" << " v: print program version." << "\n" - << " h: display this help messsage." << "\n" + << " h: display this help message." << "\n" << " --haplotypes: data were phased as RAD locus haplotypes.\n" << " --dprime-bin-size: size of buckets for binning SNPs at a particular distance to calculate the mean D' value.\n" << " --dprime-threshold : if D' values fall above , set the D' to 1, otherwise set D' to 0.\n\n" --- stacks.orig/src/populations.cc +++ stacks/src/populations.cc @@ -720,7 +720,7 @@ do { int rv = this->_fasta_reader.next_seq(seq); if (rv == 0) { - cerr << "Error: catalog VCF and FASTA files are discordant, maybe trucated. rv: " + cerr << "Error: catalog VCF and FASTA files are discordant, maybe truncated. rv: " << rv << "; cloc_id: " << cloc_id << "\n"; throw exception(); } @@ -4270,7 +4270,7 @@ } if (merge_sites == true && enz.length() == 0) { - cerr << "Error: You must specify the restriction enzyme associated with this data set to merge overlaping cutsites.\n"; + cerr << "Error: You must specify the restriction enzyme associated with this data set to merge overlapping cutsites.\n"; help(); } @@ -4297,7 +4297,7 @@ << "populations -P dir [-O dir] [-M popmap] (filters) [--fstats] [-k [--sigma=150000] [--bootstrap [-N 100]]] (output formats)\n" << "populations -V vcf -O dir [-M popmap] (filters) [--fstats] [-k [--sigma=150000] [--bootstrap [-N 100]]] (output formats)\n" << "\n" - << " -P,--in-path: path to a directory containing Stacks ouput files.\n" + << " -P,--in-path: path to a directory containing Stacks output files.\n" << " -V,--in-vcf: path to a standalone input VCF file.\n" << " -O,--out-path: path to a directory where to write the output files. (Required by -V; otherwise defaults to value of -P.)\n" << " -M,--popmap: path to a population map. (Format is 'SAMPLE1 \\t POP1 \\n SAMPLE2 ...'.)\n" @@ -4373,7 +4373,7 @@ << " --map-format: mapping program format to write, 'joinmap', 'onemap', and 'rqtl' are currently supported.\n" << "\n" << "Additional options:\n" - << " -h,--help: display this help messsage.\n" + << " -h,--help: display this help message.\n" << " -v,--version: print program version.\n" << " --verbose: turn on additional logging.\n" << (" --log-fst-comp: log components of Fst/Phi_st calculations to a file.\n") --- stacks.orig/src/gstacks.cc +++ stacks/src/gstacks.cc @@ -485,7 +485,7 @@ << cs.mean_olapd_locus_length() << ";\n" << " Out of " << cs.n_tot_reads << " paired-end reads in these loci (mean " << (double) cs.n_aln_reads / pe_ctg << " reads per locus),\n" - << " " << cs.n_aln_reads << " were successfuly aligned (" + << " " << cs.n_aln_reads << " were successfully aligned (" << as_percentage((double) cs.n_aln_reads / cs.n_tot_reads) << ");\n" << " Mean insert length was " << cs.insert_length_olap_mv.mean() << ", stdev: " << cs.insert_length_olap_mv.sd_p() << " (based on aligned reads in overlapped loci).\n"; @@ -3090,7 +3090,7 @@ "De novo mode:\n" " gstacks -P stacks_dir -M popmap\n" "\n" - " -P: input directory containg '*.matches.bam' files created by the\n" + " -P: input directory containing '*.matches.bam' files created by the\n" " de novo Stacks pipeline, ustacks-cstacks-sstacks-tsv2bam\n" "\n" "Reference-based mode:\n" --- stacks.orig/src/ustacks.cc +++ stacks/src/ustacks.cc @@ -2981,7 +2981,7 @@ if (in_file_type == FileT::unknown) { in_file_type = guess_file_type(in_file); if (in_file_type == FileT::unknown) { - cerr << "Unable to recongnize the extention of file '" << in_file << "'.\n"; + cerr << "Unable to recongnize the extension of file '" << in_file << "'.\n"; help(); } } @@ -3033,7 +3033,7 @@ << " -H: disable calling haplotypes from secondary reads.\n" << "\n" << " Stack assembly options:\n" - << " --force-diff-len: allow raw input reads of different lengths, e.g. after trimming (default: ustacks perfers raw input reads of uniform length).\n" + << " --force-diff-len: allow raw input reads of different lengths, e.g. after trimming (default: ustacks prefers raw input reads of uniform length).\n" << " --keep-high-cov: disable the algorithm that removes highly-repetitive stacks and nearby errors.\n" << " --high-cov-thres: highly-repetitive stacks threshold, in standard deviation units (default: 3.0).\n" << " --max-locus-stacks : maximum number of stacks at a single de novo locus (default 3).\n" @@ -3053,7 +3053,7 @@ << " For the Fixed model:\n" << " --bc-err-freq : specify the barcode error frequency, between 0 and 1.0.\n" << "\n" - << " h: display this help messsage.\n"; + << " h: display this help message.\n"; exit(1); }