From e7536c15d87cf6da6a3a426ee34cdb2f64676222 Mon Sep 17 00:00:00 2001
From: Marco Biasini <marco.biasini@unibas.ch>
Date: Tue, 9 Aug 2011 11:11:45 +0200
Subject: [PATCH] strip whitespace characters from SEQRES entries
---
modules/base/src/string_ref.cc | 13 +++++++++++++
modules/base/src/string_ref.hh | 4 ++++
modules/io/src/mol/mmcif_reader.cc | 7 ++++---
3 files changed, 21 insertions(+), 3 deletions(-)
diff --git a/modules/base/src/string_ref.cc b/modules/base/src/string_ref.cc
index 5cc42986b..6a1d62254 100644
--- a/modules/base/src/string_ref.cc
+++ b/modules/base/src/string_ref.cc
@@ -113,4 +113,17 @@ std::vector<StringRef> StringRef::split(char p) const
return result;
}
+std::string StringRef::str_no_whitespace() const
+{
+ std::string whitespaceless_string;
+ whitespaceless_string.reserve(this->size());
+ for (const char* s=begin_; s!=end_; ++s) {
+ if (isspace(*s)) {
+ continue;
+ }
+ whitespaceless_string.push_back(*s);
+
+ }
+ return whitespaceless_string;
+}
}
diff --git a/modules/base/src/string_ref.hh b/modules/base/src/string_ref.hh
index cc5661eba..d72a27a85 100644
--- a/modules/base/src/string_ref.hh
+++ b/modules/base/src/string_ref.hh
@@ -147,6 +147,10 @@ public:
/// \brief split string into chunks delimited by \p p
std::vector<StringRef> split(char p) const;
+
+ /// \brief returns a new string with all whitespace removed from
+ /// this StringRef
+ std::string str_no_whitespace() const;
private:
const char* begin_;
const char* end_;
diff --git a/modules/io/src/mol/mmcif_reader.cc b/modules/io/src/mol/mmcif_reader.cc
index b766d74fb..98c357225 100644
--- a/modules/io/src/mol/mmcif_reader.cc
+++ b/modules/io/src/mol/mmcif_reader.cc
@@ -518,22 +518,23 @@ void MMCifParser::ParseEntityPoly(const std::vector<StringRef>& columns)
this->GetCurrentLinenum()));
}
if (read_seqres_) {
+ StringRef seqres;
if (seqres_can_) {
if (indices_[PDBX_SEQ_ONE_LETTER_CODE_CAN] != -1) {
- edm_it->second.seqres =
- columns[indices_[PDBX_SEQ_ONE_LETTER_CODE_CAN]].str();
+ seqres=columns[indices_[PDBX_SEQ_ONE_LETTER_CODE_CAN]];
} else {
throw IOException(this->FormatDiagnostic(STAR_DIAG_ERROR,
"'entity_poly.pdbx_seq_one_letter_code_can' not available.'",
this->GetCurrentLinenum()));
}
} else if (indices_[PDBX_SEQ_ONE_LETTER_CODE] != -1) {
- edm_it->second.seqres = columns[indices_[PDBX_SEQ_ONE_LETTER_CODE]].str();
+ seqres=columns[indices_[PDBX_SEQ_ONE_LETTER_CODE]];
} else {
throw IOException(this->FormatDiagnostic(STAR_DIAG_ERROR,
"'entity_poly.pdbx_seq_one_letter_code' not available.'",
this->GetCurrentLinenum()));
}
+ edm_it->second.seqres = seqres.str_no_whitespace();
}
}
--
GitLab