Created
August 26, 2012 04:25
-
-
Save mtholder/3474043 to your computer and use it in GitHub Desktop.
Reads a phylogenetic tree or data file and prints out the taxa labels one per line
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
// Copyright (C) 2012 Mark T. Holder | |
// | |
// Based on example/splitsinfile/splitsinfile.cpp in NEXUS class library | |
// | |
// After NCL has been installed at ${NCL_PREFIX} | |
// | |
// g++ newick2taxalist.cpp -o newick2taxalist -I "${NCL_PREFIX}/include" -lncl -L "${NCL_PREFIX}/lib/ncl" | |
// | |
// Takes a newick file and prints out the taxa labels, one per line. | |
// | |
// This script is free software; you can redistribute it and/or modify | |
// it under the terms of the GNU General Public License as published by | |
// the Free Software Foundation; either version 2 of the License, or | |
// (at your option) any later version. | |
// | |
// This script is distributed in the hope that it will be useful, | |
// but WITHOUT ANY WARRANTY; without even the implied warranty of | |
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the | |
// GNU General Public License for more details. | |
// | |
// You should have received a copy of the GNU General Public License | |
// along with NCL; if not, write to the Free Software Foundation, Inc., | |
// 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA | |
// | |
#include "ncl/ncl.h" | |
#include "ncl/nxsblock.h" | |
#include "ncl/nxspublicblocks.h" | |
#include "ncl/nxsmultiformat.h" | |
#include <cassert> | |
using namespace std; | |
long gStrictLevel = 2; | |
long gInterleaveLen = -1; | |
bool gVerbose = false; | |
void processContent(PublicNexusReader & nexusReader, ostream *out); | |
//////////////////////////////////////////////////////////////////////////////// | |
// Takes NxsReader that has successfully read a file, and processes the | |
// information stored in the reader. | |
// | |
// The caller is responsibel for calling DeleteBlocksFromFactories() to clean | |
// up (if the reader uses the factory API). | |
//////////////////////////////////////////////////////////////////////////////// | |
void processContent(PublicNexusReader & nexusReader, ostream *out) | |
{ | |
if (!out) | |
return; | |
BlockReaderList blocks = nexusReader.GetUsedBlocksInOrder(); | |
for (BlockReaderList::const_iterator bIt = blocks.begin(); bIt != blocks.end(); ++bIt) | |
{ | |
NxsBlock * b = *bIt; | |
if (b->GetID() == "TAXA") | |
{ | |
NxsTaxaBlockAPI * tb = (NxsTaxaBlockAPI *)b; | |
std::vector<std::string> labVec = tb->GetAllLabels(); | |
std::vector<std::string>::const_iterator vIt = labVec.begin(); | |
for (; vIt != labVec.end(); ++vIt) | |
{ | |
*out << *vIt << '\n'; | |
} | |
} | |
} | |
} | |
//////////////////////////////////////////////////////////////////////////////// | |
// Creates a NxsReader, and tries to read the file `filename`. If the | |
// read succeeds, then processContent will be called. | |
//////////////////////////////////////////////////////////////////////////////// | |
void processFilepath( | |
const char * filename, // name of the file to be read | |
ostream *out, // output stream to use (NULL for no output). Not that cerr is used to report errors. | |
MultiFormatReader::DataFormatType fmt) // enum indicating the file format to expect. | |
{ | |
assert(filename); | |
try | |
{ | |
MultiFormatReader nexusReader(-1, NxsReader::WARNINGS_TO_STDERR); | |
if (gStrictLevel != 2) | |
nexusReader.SetWarningToErrorThreshold((int)NxsReader::FATAL_WARNING + 1 - (int) gStrictLevel); | |
nexusReader.SetWarningOutputLevel(NxsReader::SUPPRESS_WARNINGS_LEVEL); | |
NxsCharactersBlock * charsB = nexusReader.GetCharactersBlockTemplate(); | |
NxsDataBlock * dataB = nexusReader.GetDataBlockTemplate(); | |
charsB->SetAllowAugmentingOfSequenceSymbols(true); | |
dataB->SetAllowAugmentingOfSequenceSymbols(true); | |
if (gInterleaveLen > 0) | |
{ | |
assert(charsB); | |
charsB->SetWriteInterleaveLen(gInterleaveLen); | |
dataB->SetWriteInterleaveLen(gInterleaveLen); | |
} | |
NxsTreesBlock * treesB = nexusReader.GetTreesBlockTemplate(); | |
assert(treesB); | |
if (gStrictLevel < 2) | |
treesB->SetAllowImplicitNames(true); | |
if (gStrictLevel < 2) | |
{ | |
NxsStoreTokensBlockReader *storerB = nexusReader.GetUnknownBlockTemplate(); | |
assert(storerB); | |
storerB->SetTolerateEOFInBlock(true); | |
} | |
try { | |
nexusReader.ReadFilepath(filename, fmt); | |
processContent(nexusReader, out); | |
} | |
catch(...) | |
{ | |
nexusReader.DeleteBlocksFromFactories(); | |
throw; | |
} | |
nexusReader.DeleteBlocksFromFactories(); | |
} | |
catch (const NxsException &x) | |
{ | |
cerr << "Error:\n " << x.msg << endl; | |
if (x.line >=0) | |
cerr << "at line " << x.line << ", column (approximately) " << x.col << " (and file position "<< x.pos << ")" << endl; | |
exit(2); | |
} | |
} | |
void readFilepathAsNEXUS(const char *filename, MultiFormatReader::DataFormatType fmt) | |
{ | |
cerr << "[Reading " << filename << " ]" << endl; | |
try { | |
ostream * outStream = 0L; | |
outStream = &cout; | |
processFilepath(filename, outStream, fmt); | |
} | |
catch (...) | |
{ | |
cerr << "Parsing of " << filename << " failed (with an exception)" << endl; | |
exit(1); | |
} | |
} | |
void readFilesListedIsFile(const char *masterFilepath, MultiFormatReader::DataFormatType fmt) | |
{ | |
ifstream masterStream(masterFilepath, ios::binary); | |
if (masterStream.bad()) | |
{ | |
cerr << "Could not open " << masterFilepath << "." << endl; | |
exit(3); | |
} | |
char filename[1024]; | |
while ((!masterStream.eof()) && masterStream.good()) | |
{ | |
masterStream.getline(filename, 1024); | |
if (strlen(filename) > 0 && filename[0] != '#') | |
readFilepathAsNEXUS(filename, fmt); | |
} | |
} | |
void printHelp(ostream & out) | |
{ | |
out << "newick2taxalist takes a file and prints out the taxa labels, one per line.\n"; | |
out << "\nThe most common usage is simply:\n newick2taxalist <path to NEXUS file>\n"; | |
out << "\nCommand-line flags:\n\n"; | |
out << " -h on the command line shows this help message\n\n"; | |
out << " -v verbose output\n\n"; | |
out << " -l<path> reads a file and treats each line of the file as a path to NEXUS file\n\n"; | |
out << " -s<non-negative integer> controls the NEXUS strictness level.\n"; | |
out << " the default level is equivalent to -s2 invoking the program with \n"; | |
out << " -s3 or a higher number will convert some warnings into fatal errors.\n"; | |
out << " Running with -s1 will cause the parser to accept dangerous constructs,\n"; | |
out << " and running with -s0 will cause the parser make every attempt to finish\n"; | |
out << " parsing the file (warning about very serious errors).\n\n"; | |
out << " Note that when -s0 strictness level is used, and the parser fails to\n"; | |
out << " finish, it will often be the result of an earlier error than the \n"; | |
out << " error that is reported in the last message.\n"; | |
out << " -f<format> specifies the input file format expected:\n"; | |
out << " -fnexus NEXUS (this is also the default)\n"; | |
out << " -faafasta Amino acid data in fasta\n"; | |
out << " -fdnafasta DNA data in fasta\n"; | |
out << " -frnafasta RNA data in fasta\n"; | |
out << " The complete list of format names that can follow the -f flag is:\n"; | |
std::vector<std::string> fmtNames = MultiFormatReader::getFormatNames(); | |
for (std::vector<std::string>::const_iterator n = fmtNames.begin(); n != fmtNames.end(); ++n) | |
{ | |
out << " "<< *n << "\n"; | |
} | |
} | |
int main(int argc, char *argv[]) | |
{ | |
MultiFormatReader::DataFormatType f(MultiFormatReader::NEXUS_FORMAT); | |
bool readfile = false; | |
for (int i = 1; i < argc; ++i) | |
{ | |
const char * filepath = argv[i]; | |
const unsigned slen = strlen(filepath); | |
if (strlen(filepath) > 1 && filepath[0] == '-' && filepath[1] == 'h') | |
printHelp(cout); | |
else if (strlen(filepath) == 2 && filepath[0] == '-' && filepath[1] == 'v') | |
gVerbose = true; | |
else if (slen > 1 && filepath[0] == '-' && filepath[1] == 's') | |
{ | |
if ((slen == 2) || (!NxsString::to_long(filepath + 2, &gStrictLevel))) | |
{ | |
cerr << "Expecting an integer after -s\n" << endl; | |
printHelp(cerr); | |
return 2; | |
} | |
} | |
else if (slen > 1 && filepath[0] == '-' && filepath[1] == 'f') | |
{ | |
f = MultiFormatReader::UNSUPPORTED_FORMAT; | |
if (slen > 2) | |
{ | |
std::string fmtName(filepath + 2, slen - 2); | |
f = MultiFormatReader::formatNameToCode(fmtName); | |
} | |
if (f == MultiFormatReader::UNSUPPORTED_FORMAT) | |
{ | |
cerr << "Expecting a format after after -f\n" << endl; | |
printHelp(cerr); | |
return 2; | |
} | |
} | |
else | |
{ | |
if (strlen(filepath) > 2 && filepath[0] == '-' && filepath[1] == 'l') | |
{ | |
readfile = true; | |
readFilesListedIsFile(filepath+2, f); | |
} | |
else | |
{ | |
readfile = true; | |
readFilepathAsNEXUS(filepath, f); | |
} | |
} | |
} | |
if (!readfile) | |
{ | |
cerr << "Expecting the path to NEXUS file as the only command line argument!\n" << endl; | |
printHelp(cerr); | |
return 1; | |
} | |
return 0; | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment