/*------------------------------------------------------------------------
* object to WKT
*/
bool ogc_method :: to_wkt_projection(
char buffer[],
int options,
size_t buflen) const
{
OGC_UTF8_NAME buf_name;
OGC_TBUF buf_hdr;
OGC_TBUF buf_id;
int opts = (options | OGC_WKT_OPT_INTERNAL);
size_t len = 0;
bool rc = true;
const char * opn = "[";
const char * cls = "]";
const char * kwd = obj_kwd();
if ( (options & OGC_WKT_OPT_PARENS) != 0 )
{
opn = "(";
cls = ")";
}
if ( (opts & OGC_WKT_OPT_TOP_ID_ONLY) != 0 )
opts |= OGC_WKT_OPT_NO_IDS;
if ( buffer == OGC_NULL )
return false;
*buffer = 0;
if ( (opts & OGC_WKT_OPT_OLD_SYNTAX) != 0 )
kwd = alt_kwd();
ogc_string::escape_str(buf_name, _name, OGC_UTF8_NAME_MAX);
sprintf(buf_hdr, "%s%s\"%s\"",
kwd, opn, buf_name);
OGC_CPY_TO_BUF( buf_hdr );
if ( _ids != OGC_NULL && (options & OGC_WKT_OPT_NO_IDS) == 0 )
{
for (int i = 0; i < id_count(); i++)
{
rc &= ogc_id :: to_wkt(id(i), buf_id, opts, OGC_TBUF_MAX);
OGC_ADD_TO_BUF( buf_id );
if ( (opts & OGC_WKT_OPT_OLD_SYNTAX) != 0 )
break;
}
}
OGC_CPY_TO_BUF( cls );
if ( (options & OGC_WKT_OPT_INTERNAL) == 0 &&
(options & OGC_WKT_OPT_EXPAND) != 0 )
{
rc &= ogc_utils :: expand_wkt(buffer, buffer, "", options, buflen);
}
return rc;
}
bool ogc_cs :: to_wkt(
char buffer[],
int options,
size_t buflen) const
{
OGC_TBUF buf_hdr;
OGC_TBUF buf_id;
OGC_NBUF buf_dimension;
const char * cs_type;
int opts = (options | OGC_WKT_OPT_INTERNAL);
size_t len = 0;
bool rc = true;
const char * opn = "[";
const char * cls = "]";
const char * kwd = obj_kwd();
if ( (options & OGC_WKT_OPT_PARENS) != 0 )
{
opn = "(";
cls = ")";
}
if ( (opts & OGC_WKT_OPT_TOP_ID_ONLY) != 0 )
opts |= OGC_WKT_OPT_NO_IDS;
if ( buffer == OGC_NULL )
return false;
*buffer = 0;
if ( (options & OGC_WKT_OPT_OLD_SYNTAX) != 0 )
return true;
cs_type = ogc_utils :: cs_type_to_kwd(_cs_type);
ogc_string :: itoa(_dimension, buf_dimension);
sprintf(buf_hdr, "%s%s\"%s\",%s",
kwd, opn, cs_type, buf_dimension);
OGC_CPY_TO_BUF( buf_hdr );
if ( _ids != OGC_NULL && (options & OGC_WKT_OPT_NO_IDS) == 0 )
{
for (int i = 0; i < id_count(); i++)
{
rc &= ogc_id :: to_wkt(id(i), buf_id, opts, OGC_TBUF_MAX);
OGC_ADD_TO_BUF( buf_id );
if ( (options & OGC_WKT_OPT_OLD_SYNTAX) != 0 )
break;
}
}
OGC_CPY_TO_BUF( cls );
if ( (options & OGC_WKT_OPT_INTERNAL) == 0 &&
(options & OGC_WKT_OPT_EXPAND) != 0 )
{
rc &= ogc_utils :: expand_wkt(buffer, buffer, "", options, buflen);
}
return rc;
}
bool ogc_geog3d_crs :: to_wkt(
char buffer[],
int options,
size_t buflen) const
{
OGC_UTF8_NAME buf_name;
OGC_TBUF buf_hdr;
OGC_TBUF buf_datum;
OGC_TBUF buf_primem;
OGC_TBUF buf_cs;
OGC_TBUF buf_axis_1;
OGC_TBUF buf_axis_2;
OGC_TBUF buf_axis_3;
OGC_TBUF buf_unit;
OGC_TBUF buf_extent;
OGC_TBUF buf_id;
OGC_TBUF buf_remark;
int opts = (options | OGC_WKT_OPT_INTERNAL);
size_t len = 0;
bool rc = true;
const char * opn = "[";
const char * cls = "]";
const char * kwd = obj_kwd();
if ( (options & OGC_WKT_OPT_PARENS) != 0 )
{
opn = "(";
cls = ")";
}
if ( (opts & OGC_WKT_OPT_TOP_ID_ONLY) != 0 )
opts |= OGC_WKT_OPT_NO_IDS;
if ( buffer == OGC_NULL )
return false;
*buffer = 0;
if ( (opts & OGC_WKT_OPT_OLD_SYNTAX) != 0 )
return true;
rc &= ogc_geodetic_datum :: to_wkt(_datum, buf_datum, opts, OGC_TBUF_MAX);
rc &= ogc_primem :: to_wkt(_primem, buf_primem, opts, OGC_TBUF_MAX);
rc &= ogc_cs :: to_wkt(_cs, buf_cs, opts, OGC_TBUF_MAX);
rc &= ogc_axis :: to_wkt(_axis_1, buf_axis_1, opts, OGC_TBUF_MAX);
rc &= ogc_axis :: to_wkt(_axis_2, buf_axis_2, opts, OGC_TBUF_MAX);
rc &= ogc_axis :: to_wkt(_axis_3, buf_axis_3, opts, OGC_TBUF_MAX);
rc &= ogc_unit :: to_wkt(_unit, buf_unit, opts, OGC_TBUF_MAX);
rc &= ogc_remark :: to_wkt(_remark, buf_remark, opts, OGC_TBUF_MAX);
ogc_string::escape_str(buf_name, _name, OGC_UTF8_NAME_MAX);
sprintf(buf_hdr, "%s%s\"%s\"",
kwd, opn, buf_name);
OGC_CPY_TO_BUF( buf_hdr );
OGC_ADD_TO_BUF( buf_datum );
OGC_ADD_TO_BUF( buf_primem );
OGC_ADD_TO_BUF( buf_cs );
OGC_ADD_TO_BUF( buf_axis_1 );
OGC_ADD_TO_BUF( buf_axis_2 );
OGC_ADD_TO_BUF( buf_axis_3 );
OGC_ADD_TO_BUF( buf_unit );
if ( _extents != OGC_NULL && (options & OGC_WKT_OPT_OLD_SYNTAX) == 0 )
{
for (int i = 0; i < extent_count(); i++)
{
rc &= ogc_extent :: to_wkt(extent(i), buf_extent, opts, OGC_TBUF_MAX);
OGC_ADD_TO_BUF( buf_extent );
}
}
if ( _ids != OGC_NULL && (options & OGC_WKT_OPT_NO_IDS) == 0 )
{
for (int i = 0; i < id_count(); i++)
{
rc &= ogc_id :: to_wkt(id(i), buf_id, opts, OGC_TBUF_MAX);
OGC_ADD_TO_BUF( buf_id );
}
}
OGC_ADD_TO_BUF( buf_remark );
OGC_CPY_TO_BUF( cls );
if ( (options & OGC_WKT_OPT_INTERNAL) == 0 &&
(options & OGC_WKT_OPT_EXPAND) != 0 )
{
rc &= ogc_utils :: expand_wkt(buffer, buffer, "", options, buflen);
}
return rc;
}
bool ogc_unit :: to_wkt(
char buffer[],
int options,
size_t buflen) const
{
OGC_UTF8_NAME buf_name;
OGC_TBUF buf_hdr;
OGC_TBUF buf_id;
OGC_NBUF buf_factor;
int opts = (options | OGC_WKT_OPT_INTERNAL);
size_t len = 0;
bool rc = true;
const char * opn = "[";
const char * cls = "]";
const char * kwd = obj_kwd();
if ( (options & OGC_WKT_OPT_PARENS) != 0 )
{
opn = "(";
cls = ")";
}
if ( (opts & OGC_WKT_OPT_TOP_ID_ONLY) != 0 )
opts |= OGC_WKT_OPT_NO_IDS;
if ( buffer == OGC_NULL )
return false;
*buffer = 0;
if ( !is_visible() )
return true;
ogc_string :: dtoa(_factor, buf_factor);
if ( (options & OGC_WKT_OPT_OLD_SYNTAX) == 0 )
{
switch (_unit_type)
{
case OGC_UNIT_TYPE_ANGLE: kwd = ogc_angunit ::obj_kwd(); break;
case OGC_UNIT_TYPE_LENGTH: kwd = ogc_lenunit ::obj_kwd(); break;
case OGC_UNIT_TYPE_PARAM: kwd = ogc_paramunit::obj_kwd(); break;
case OGC_UNIT_TYPE_SCALE: kwd = ogc_scaleunit::obj_kwd(); break;
case OGC_UNIT_TYPE_TIME: kwd = ogc_timeunit ::obj_kwd(); break;
default:
break;
}
}
ogc_string::escape_str(buf_name, _name, OGC_UTF8_NAME_MAX);
sprintf(buf_hdr, "%s%s\"%s\",%s",
kwd, opn, buf_name, buf_factor);
OGC_CPY_TO_BUF( buf_hdr );
if ( _ids != OGC_NULL && (options & OGC_WKT_OPT_NO_IDS) == 0 )
{
for (int i = 0; i < id_count(); i++)
{
rc &= ogc_id :: to_wkt(id(i), buf_id, opts, OGC_TBUF_MAX);
OGC_ADD_TO_BUF( buf_id );
if ( (options & OGC_WKT_OPT_OLD_SYNTAX) != 0 )
break;
}
}
OGC_CPY_TO_BUF( cls );
if ( (options & OGC_WKT_OPT_INTERNAL) == 0 &&
(options & OGC_WKT_OPT_EXPAND) != 0 )
{
rc &= ogc_utils :: expand_wkt(buffer, buffer, "", options, buflen);
}
return rc;
}
void
PepNovoOutfile::load(
const std::string & result_filename,
vector<PeptideIdentification> & peptide_identifications,
ProteinIdentification & protein_identification,
const double & score_threshold,
const IndexPosMappingType & index_to_precursor,
const map<String, String> & pnovo_modkey_to_mod_id
)
{
// generally used variables
StringList substrings;
map<String, Int> columns;
PeptideHit peptide_hit;
String
line,
score_type = "PepNovo",
version = "unknown",
identifier,
filename,
sequence,
sequence_with_mods;
DateTime datetime = DateTime::now(); // there's no date given from PepNovo
protein_identification.setDateTime(datetime);
peptide_identifications.clear();
PeptideIdentification peptide_identification;
protein_identification = ProteinIdentification();
// open the result
ifstream result_file(result_filename.c_str());
if (!result_file)
{
throw Exception::FileNotFound(__FILE__, __LINE__, OPENMS_PRETTY_FUNCTION, result_filename);
}
Size line_number(0); // used to report in which line an error occurred
Size id_count(0); // number of IDs seen (not necessarily the ones finally returned)
getSearchEngineAndVersion(result_filename, protein_identification);
//if information could not be retrieved from the outfile use defaults
if (protein_identification.getSearchEngineVersion().empty())
{
protein_identification.setSearchEngine("PepNovo");
protein_identification.setSearchEngineVersion(version);
}
identifier = protein_identification.getSearchEngine() + "_" + datetime.getDate();
protein_identification.setIdentifier(identifier);
map<String, String> mod_mask_map;
const vector<String> & mods = protein_identification.getSearchParameters().variable_modifications;
for (vector<String>::const_iterator mod_it = mods.begin(); mod_it != mods.end(); ++mod_it)
{
if (mod_it->empty())
continue;
//cout<<*mod_it<<endl;
if (pnovo_modkey_to_mod_id.find(*mod_it) != pnovo_modkey_to_mod_id.end())
{
//cout<<keys_to_id.find(*mod_it)->second<<endl;
ResidueModification tmp_mod = ModificationsDB::getInstance()->getModification(pnovo_modkey_to_mod_id.find(*mod_it)->second);
if (mod_it->prefix(1) == "^" || mod_it->prefix(1) == "$")
{
mod_mask_map[*mod_it] = "(" + tmp_mod.getId() + ")";
}
else
{
mod_mask_map[*mod_it] = String(tmp_mod.getOrigin()) + "(" + tmp_mod.getId() + ")";
}
}
else
{
if (mod_it->prefix(1) != "^" && mod_it->prefix(1) != "$")
{
mod_mask_map[*mod_it] = mod_it->prefix(1) + "[" + mod_it->substr(1) + "]";
//cout<<mod_mask_map[*mod_it]<<endl;
}
else
{
mod_mask_map[*mod_it] = "[" + *mod_it + "]";
//cout<<mod_mask_map[*mod_it]<<endl;
}
}
}
Size index;
while (getline(result_file, line))
{
if (!line.empty() && (line[line.length() - 1] < 33)) line.resize(line.length() - 1); // remove weird EOL character
line.trim();
++line_number;
if (line.hasPrefix(">> ")) // >> 1 /home/shared/pepnovo/4611_raw_ms2_picked.mzXML.1001.2.dta
{
++id_count;
if (!peptide_identification.empty() && !peptide_identification.getHits().empty())
{
peptide_identifications.push_back(peptide_identification);
}
line.split(' ', substrings);
//String index = File::basename(line.substr(line.find(' ', strlen(">> ")) + 1));
if (substrings.size() < 3)
{
throw Exception::ParseError(__FILE__, __LINE__, OPENMS_PRETTY_FUNCTION, "Not enough columns (spectrum Id) in file in line " + String(line_number) + String(" (should be 2 or more)!"), result_filename);
}
try
{
index = substrings[2].trim().toInt();
}
catch (...)
{
throw Exception::ParseError(__FILE__, __LINE__, OPENMS_PRETTY_FUNCTION, "Expected an index number in line " + String(line_number) + String(" at position 2 (line was: '" + line + "')!"), result_filename);
}
//cout<<"INDEX: "<<index<<endl;
peptide_identification = PeptideIdentification();
bool success = false;
if (index_to_precursor.size()>0)
{
if (index_to_precursor.find(index) != index_to_precursor.end())
{
peptide_identification.setRT(index_to_precursor.find(index)->second.first);
peptide_identification.setMZ(index_to_precursor.find(index)->second.second);
success = true;
}
else throw Exception::ParseError(__FILE__, __LINE__, OPENMS_PRETTY_FUNCTION, "Index '" + String(index) + String("' in line '" + line + "' not found in index table (line was: '" + line + "')!"), result_filename);
}
if (!success)
{ // try to reconstruct from title entry (usually sensible when MGF is supplied to PepNovo)
try
{
if (substrings.size() >= 4)
{
StringList parts = ListUtils::create<String>(substrings[3], '_');
if (parts.size() >= 2)
{
peptide_identification.setRT(parts[1].toDouble());
peptide_identification.setMZ(parts[0].toDouble());
success = true;
}
}
}
catch (...)
{
}
if (!success) throw Exception::ParseError(__FILE__, __LINE__, OPENMS_PRETTY_FUNCTION, "Precursor could not be reconstructed from title '" + substrings[3] + String("' in line '" + line + "' (line was: '" + line + "')!"), result_filename);
}
peptide_identification.setSignificanceThreshold(score_threshold);
peptide_identification.setScoreType(score_type);
peptide_identification.setIdentifier(identifier);
}
else if (line.hasPrefix("#Index")) // #Index Prob Score N-mass C-Mass [M+H] Charge Sequence
{
if (columns.empty()) // map the column names to their column number
{
line.split('\t', substrings);
for (vector<String>::const_iterator s_i = substrings.begin(); s_i != substrings.end(); ++s_i)
{
if ((*s_i) == "#Index")
columns["Index"] = s_i - substrings.begin();
else if ((*s_i) == "RnkScr")
columns["RnkScr"] = s_i - substrings.begin();
else if ((*s_i) == "PnvScr")
columns["PnvScr"] = s_i - substrings.begin();
else if ((*s_i) == "N-Gap")
columns["N-Gap"] = s_i - substrings.begin();
else if ((*s_i) == "C-Gap")
columns["C-Gap"] = s_i - substrings.begin();
else if ((*s_i) == "[M+H]")
columns["[M+H]"] = s_i - substrings.begin();
else if ((*s_i) == "Charge")
columns["Charge"] = s_i - substrings.begin();
else if ((*s_i) == "Sequence")
columns["Sequence"] = s_i - substrings.begin();
}
if (columns.size() != 8)
{
result_file.close();
result_file.clear();
throw Exception::ParseError(__FILE__, __LINE__, OPENMS_PRETTY_FUNCTION, "Not enough columns in file in line " + String(line_number) + String(" (should be 8)!"), result_filename);
}
}
while (getline(result_file, line))
{
++line_number;
if (!line.empty() && (line[line.length() - 1] < 33))
line.resize(line.length() - 1);
line.trim();
if (line.empty())
break;
line.split('\t', substrings);
if (!substrings.empty())
{
if (substrings.size() != 8)
{
result_file.close();
result_file.clear();
throw Exception::ParseError(__FILE__, __LINE__, OPENMS_PRETTY_FUNCTION, "Not enough columns in file in line " + String(line_number) + String(" (should be 8)!"), result_filename);
}
if (substrings[columns["RnkScr"]].toFloat() >= score_threshold)
{
peptide_hit = PeptideHit();
peptide_hit.setCharge(substrings[columns["Charge"]].toInt());
peptide_hit.setRank(substrings[columns["Index"]].toInt() + 1);
peptide_hit.setScore(substrings[columns["RnkScr"]].toFloat());
peptide_hit.setMetaValue("PnvScr", substrings[columns["PnvScr"]].toFloat());
peptide_hit.setMetaValue("N-Gap", substrings[columns["N-Gap"]].toFloat());
peptide_hit.setMetaValue("C-Gap", substrings[columns["C-Gap"]].toFloat());
peptide_hit.setMetaValue("MZ", substrings[columns["[M+H]"]].toFloat());
sequence = substrings[columns["Sequence"]];
for (map<String, String>::iterator mask_it = mod_mask_map.begin(); mask_it != mod_mask_map.end(); ++mask_it)
{
if (mask_it->first.hasPrefix("^") && sequence.hasSubstring(mask_it->first))
{
sequence.substitute(mask_it->first, "");
sequence = mask_it->second + sequence;
}
//cout<<mask_it->first<<" "<<mask_it->second<<endl;
sequence.substitute(mask_it->first, mask_it->second);
}
peptide_hit.setSequence(AASequence::fromString(sequence));
peptide_identification.insertHit(peptide_hit);
}
}
}
}
}
if (!peptide_identifications.empty() || !peptide_identification.getHits().empty())
{
peptide_identifications.push_back(peptide_identification);
}
result_file.close();
result_file.clear();
LOG_INFO << "Parsed " << id_count << " ids, retained " << peptide_identifications.size() << "." << std::endl;
}
bool ogc_ellipsoid :: to_wkt(
char buffer[],
int options,
size_t buflen) const
{
OGC_UTF8_NAME buf_name;
OGC_TBUF buf_hdr;
OGC_TBUF buf_lenunit;
OGC_TBUF buf_id;
OGC_NBUF buf_sm_axis;
OGC_NBUF buf_flattening;
int opts = (options | OGC_WKT_OPT_INTERNAL);
size_t len = 0;
bool rc = true;
const char * opn = "[";
const char * cls = "]";
const char * kwd = obj_kwd();
if ( (options & OGC_WKT_OPT_PARENS) != 0 )
{
opn = "(";
cls = ")";
}
if ( (opts & OGC_WKT_OPT_TOP_ID_ONLY) != 0 )
opts |= OGC_WKT_OPT_NO_IDS;
if ( buffer == OGC_NULL )
return false;
*buffer = 0;
if ( !is_visible() )
return true;
if ( (options & OGC_WKT_OPT_OLD_SYNTAX) != 0 )
kwd = alt_kwd();
double flattening = _flattening;
if ( flattening != 0.0 )
flattening = (1.0 / flattening);
ogc_string :: dtoa(_semi_major_axis, buf_sm_axis);
ogc_string :: dtoa( flattening, buf_flattening);
if ( (options & OGC_WKT_OPT_OLD_SYNTAX) == 0 )
rc &= ogc_lenunit :: to_wkt(_lenunit, buf_lenunit, opts, OGC_TBUF_MAX);
else
*buf_lenunit = 0;
ogc_string::escape_str(buf_name, _name, OGC_UTF8_NAME_MAX);
sprintf(buf_hdr, "%s%s\"%s\",%s,%s",
kwd, opn, buf_name, buf_sm_axis, buf_flattening);
OGC_CPY_TO_BUF( buf_hdr );
OGC_ADD_TO_BUF( buf_lenunit );
if ( _ids != OGC_NULL && (options & OGC_WKT_OPT_NO_IDS) == 0 )
{
for (int i = 0; i < id_count(); i++)
{
rc &= ogc_id :: to_wkt(id(i), buf_id, opts, OGC_TBUF_MAX);
OGC_ADD_TO_BUF( buf_id );
if ( (options & OGC_WKT_OPT_OLD_SYNTAX) != 0 )
break;
}
}
OGC_CPY_TO_BUF( cls );
if ( (options & OGC_WKT_OPT_INTERNAL) == 0 &&
(options & OGC_WKT_OPT_EXPAND) != 0 )
{
rc &= ogc_utils :: expand_wkt(buffer, buffer, "", options, buflen);
}
return rc;
}
