added support for reading and write gziped BEDs and TSVs

Author: diekhans

CHANGELOG.md

@@ -1,5 +1,9 @@
 # Major and user-visible changes
 
+## version 1.3.0
+* Added ability to read and write gzip compressed TSV and BED files based on an name
+  extension of '.gz'
+
 ## version 1.2.0
 * Added ability to process multiple BAMs at once.  This will use more memory
   and possibly improve the confidence scoring in some cases

configure

@@ -1,6 +1,6 @@
 #! /bin/sh
 # Guess values for system-dependent variables and create Makefiles.
-# Generated by GNU Autoconf 2.72 for intronProspector 1.2.0.
+# Generated by GNU Autoconf 2.72 for intronProspector 1.3.0.
 #
 #
 # Copyright (C) 1992-1996, 1998-2017, 2020-2023 Free Software Foundation,
@@ -600,8 +600,8 @@ MAKEFLAGS=
 # Identity of this package.
 PACKAGE_NAME='intronProspector'
 PACKAGE_TARNAME='intronprospector'
-PACKAGE_VERSION='1.2.0'
-PACKAGE_STRING='intronProspector 1.2.0'
+PACKAGE_VERSION='1.3.0'
+PACKAGE_STRING='intronProspector 1.3.0'
 PACKAGE_BUGREPORT=''
 PACKAGE_URL=''
 
@@ -1267,7 +1267,7 @@ if test "$ac_init_help" = "long"; then
   # Omit some internal or obsolete options to make the list less imposing.
   # This message is too long to be a string in the A/UX 3.1 sh.
   cat <<_ACEOF
-'configure' configures intronProspector 1.2.0 to adapt to many kinds of systems.
+'configure' configures intronProspector 1.3.0 to adapt to many kinds of systems.
 
 Usage: $0 [OPTION]... [VAR=VALUE]...
 
@@ -1330,7 +1330,7 @@ fi
 
 if test -n "$ac_init_help"; then
   case $ac_init_help in
-     short | recursive ) echo "Configuration of intronProspector 1.2.0:";;
+     short | recursive ) echo "Configuration of intronProspector 1.3.0:";;
    esac
   cat <<\_ACEOF
 
@@ -1434,7 +1434,7 @@ fi
 test -n "$ac_init_help" && exit $ac_status
 if $ac_init_version; then
   cat <<\_ACEOF
-intronProspector configure 1.2.0
+intronProspector configure 1.3.0
 generated by GNU Autoconf 2.72
 
 Copyright (C) 2023 Free Software Foundation, Inc.
@@ -1634,7 +1634,7 @@ cat >config.log <<_ACEOF
 This file contains any messages produced by compilers while
 running configure, to aid debugging if configure makes a mistake.
 
-It was created by intronProspector $as_me 1.2.0, which was
+It was created by intronProspector $as_me 1.3.0, which was
 generated by GNU Autoconf 2.72.  Invocation command line was
 
   $ $0$ac_configure_args_raw
@@ -5086,7 +5086,7 @@ cat >>$CONFIG_STATUS <<\_ACEOF || ac_write_fail=1
 # report actual input values of CONFIG_FILES etc. instead of their
 # values after options handling.
 ac_log="
-This file was extended by intronProspector $as_me 1.2.0, which was
+This file was extended by intronProspector $as_me 1.3.0, which was
 generated by GNU Autoconf 2.72.  Invocation command line was
 
   CONFIG_FILES    = $CONFIG_FILES
@@ -5141,7 +5141,7 @@ ac_cs_config_escaped=`printf "%s\n" "$ac_cs_config" | sed "s/^ //; s/'/'\\\\\\\\
 cat >>$CONFIG_STATUS <<_ACEOF || ac_write_fail=1
 ac_cs_config='$ac_cs_config_escaped'
 ac_cs_version="\\
-intronProspector config.status 1.2.0
+intronProspector config.status 1.3.0
 configured by $0, generated by GNU Autoconf 2.72,
   with options \\"\$ac_cs_config\\"
 

configure.ac

@@ -1,4 +1,4 @@
-AC_INIT([intronProspector], 1.2.0)
+AC_INIT([intronProspector], 1.3.0)
 
 ##
 # rebuild with:

docs/intronProspector.md

@@ -25,6 +25,8 @@ The `intronProspectorMerge` program can be used to convert to from the
 `--intron-calls` format to other formats as well as merge the output from
 multiple `intronProspector` runs.
 
+TSV and BED files will be automatically compressed with `gzip` if they end in `.gz`.
+
 # OPTIONS
 
 `-h, --help`

docs/intronProspectorMerge.md

@@ -11,6 +11,9 @@
 Merge output of the `intronProspector` intron calls tab-separated (TSV) files, as created by the `--intron-calls` option.
 This program can also be used to convert the output format from a single run.
 
+Compressed intron calls TSV files are recognized if they end in `.gz`.
+TSV and BED files will be automatically compressed with `gzip` if they end in `.gz`.
+
 # Options
 
 `-h, --help`

man/intronProspector.1

@@ -1,6 +1,6 @@
-.\" Automatically generated by Pandoc 3.6.3
+.\" Automatically generated by Pandoc 3.6.2
 .\"
-.TH "intronProspector" "1" "March 15, 2025" "Call intron junctions"
+.TH "intronProspector" "1" "April 10, 2025" "Call intron junctions"
 .SH NAME
 \f[B]intronProspector\f[R] \[em] Extract putative intron junctions from
 RNA\-Seq alignments
@@ -34,6 +34,9 @@ It may also improve the confidence scoring in some cases.
 The \f[CR]intronProspectorMerge\f[R] program can be used to convert to
 from the \f[CR]\-\-intron\-calls\f[R] format to other formats as well as
 merge the output from multiple \f[CR]intronProspector\f[R] runs.
+.PP
+TSV and BED files will be automatically compressed with \f[CR]gzip\f[R]
+if they end in \f[CR].gz\f[R].
 .SH OPTIONS
 \f[CR]\-h, \-\-help\f[R]
 .RS

man/intronProspectorMerge.1

@@ -1,6 +1,6 @@
-.\" Automatically generated by Pandoc 3.6.3
+.\" Automatically generated by Pandoc 3.6.2
 .\"
-.TH "intronProspectorMerge" "1" "March 15, 2025" "Merge introns junctions"
+.TH "intronProspectorMerge" "1" "April 10, 2025" "Merge introns junctions"
 .SH NAME
 \f[B]intronProspectorMerge\f[R] \[em] Merge putative introns junctions
 calls made \f[CR]intronProspector\f[R] and/or convert output formats
@@ -12,6 +12,11 @@ tab\-separated (TSV) files, as created by the
 \f[CR]\-\-intron\-calls\f[R] option.
 This program can also be used to convert the output format from a single
 run.
+.PP
+Compressed intron calls TSV files are recognized if they end in
+\f[CR].gz\f[R].
+TSV and BED files will be automatically compressed with \f[CR]gzip\f[R]
+if they end in \f[CR].gz\f[R].
 .SH Options
 \f[CR]\-h, \-\-help\f[R]
 .RS

src/AutoGzip.hh

@@ -0,0 +1,67 @@
+#ifndef autogzip_hh
+#define autogzip_hh
+
+#include <fstream>
+#include <memory>
+#include <string>
+#include "zfstream.hh"  // defines gzifstream, gzofstream
+
+static bool isGzipName(const std::string& path) {
+    return path.size() >= 3 && path.compare(path.size() - 3, 3, ".gz") == 0;
+}
+
+class AutoGzipInput : public std::istream {
+public:
+    explicit AutoGzipInput(const std::string& filename)
+        : std::istream(nullptr), filename_(filename), is_gz_(isGzipName(filename)) {
+        if (is_gz_) {
+            gz_ = std::make_unique<gzifstream>(filename_);
+            if (!gz_->is_open())
+                throw std::ios_base::failure("Failed to open gzip file: " + filename_);
+            rdbuf(gz_->rdbuf());
+        } else {
+            file_ = std::make_unique<std::ifstream>(filename_);
+            if (!file_->is_open())
+                throw std::ios_base::failure("Failed to open file: " + filename_);
+            rdbuf(file_->rdbuf());
+        }
+    }
+
+    bool is_compressed() const { return is_gz_; }
+    const std::string& filename() const { return filename_; }
+
+private:
+    const std::string filename_;
+    bool is_gz_;
+    std::unique_ptr<gzifstream> gz_;
+    std::unique_ptr<std::ifstream> file_;
+};
+
+class AutoGzipOutput : public std::ostream {
+public:
+    explicit AutoGzipOutput(const std::string& filename)
+        : std::ostream(nullptr), filename_(filename), is_gz_(isGzipName(filename)) {
+        if (is_gz_) {
+            gz_ = std::make_unique<gzofstream>(filename_);
+            if (!gz_->is_open())
+                throw std::ios_base::failure("Failed to open gzip file: " + filename_);
+            rdbuf(gz_->rdbuf());
+        } else {
+            file_ = std::make_unique<std::ofstream>(filename_);
+            if (!file_->is_open())
+                throw std::ios_base::failure("Failed to open file: " + filename_);
+            rdbuf(file_->rdbuf());
+        }
+    }
+
+    bool is_compressed() const { return is_gz_; }
+    const std::string& filename() const { return filename_; }
+
+private:
+    const std::string filename_;
+    bool is_gz_;
+    std::unique_ptr<gzofstream> gz_;
+    std::unique_ptr<std::ofstream> file_;
+};
+
+#endif