[Woc-commit] CVS: woc/bin/download Makefile.am,NONE,1.1 Makefile.in,NONE,1.1 download_pdb_from_NCI.pl.in,NONE,1.1 download_xyz_from_NCI.pl.in,NONE,1.1

[Egon W. <eg...@us...>]

Update of /cvsroot/woc/woc/bin/download
In directory usw-pr-cvs1:/tmp/cvs-serv28633/download

Added Files:
	Makefile.am Makefile.in download_pdb_from_NCI.pl.in 
	download_xyz_from_NCI.pl.in 
Log Message:
Added scripts for autodownloading of 3D coords files
from the NCI database.


--- NEW FILE: Makefile.am ---
bin_SCRIPTS = \
    download_pdb_from_NCI.pl \
    download_xyz_from_NCI.pl   

CLEANFILES = $(bin_SCRIPTS)

--- NEW FILE: Makefile.in ---
# Makefile.in generated automatically by automake 1.5 from Makefile.am.

# Copyright 1994, 1995, 1996, 1997, 1998, 1999, 2000, 2001
# Free Software Foundation, Inc.
# This Makefile.in is free software; the Free Software Foundation
# gives unlimited permission to copy and/or distribute it,
# with or without modifications, as long as this notice is preserved.

# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY, to the extent permitted by law; without
# even the implied warranty of MERCHANTABILITY or FITNESS FOR A
# PARTICULAR PURPOSE.

@SET_MAKE@

SHELL = @SHELL@

srcdir = @srcdir@
top_srcdir = @top_srcdir@
VPATH = @srcdir@
prefix = @prefix@
exec_prefix = @exec_prefix@

bindir = @bindir@
sbindir = @sbindir@
libexecdir = @libexecdir@
datadir = @datadir@
sysconfdir = @sysconfdir@
sharedstatedir = @sharedstatedir@
localstatedir = @localstatedir@
libdir = @libdir@
infodir = @infodir@
mandir = @mandir@
includedir = @includedir@
oldincludedir = /usr/include
pkgdatadir = $(datadir)/@PACKAGE@
pkglibdir = $(libdir)/@PACKAGE@
pkgincludedir = $(includedir)/@PACKAGE@
top_builddir = ../..

ACLOCAL = @ACLOCAL@
AUTOCONF = @AUTOCONF@
AUTOMAKE = @AUTOMAKE@
AUTOHEADER = @AUTOHEADER@

INSTALL = @INSTALL@
INSTALL_PROGRAM = @INSTALL_PROGRAM@
INSTALL_DATA = @INSTALL_DATA@
INSTALL_SCRIPT = @INSTALL_SCRIPT@
INSTALL_HEADER = $(INSTALL_DATA)
transform = @program_transform_name@
NORMAL_INSTALL = :
PRE_INSTALL = :
POST_INSTALL = :
NORMAL_UNINSTALL = :
PRE_UNINSTALL = :
POST_UNINSTALL = :
AMTAR = @AMTAR@
AWK = @AWK@
DEPDIR = @DEPDIR@
EXEEXT = @EXEEXT@
INSTALL_STRIP_PROGRAM = @INSTALL_STRIP_PROGRAM@
OBJEXT = @OBJEXT@
PACKAGE = @PACKAGE@
PATHTOPERL = @PATHTOPERL@
PATHTOSH = @PATHTOSH@
PATHTOXSLTPROC = @PATHTOXSLTPROC@
VERSION = @VERSION@
am__include = @am__include@
am__quote = @am__quote@
install_sh = @install_sh@

bin_SCRIPTS = \
    download_pdb_from_NCI.pl \
    download_xyz_from_NCI.pl   


CLEANFILES = $(bin_SCRIPTS)
subdir = bin/download
mkinstalldirs = $(SHELL) $(top_srcdir)/mkinstalldirs
CONFIG_CLEAN_FILES = download_pdb_from_NCI.pl download_xyz_from_NCI.pl
SCRIPTS = $(bin_SCRIPTS)

DIST_SOURCES =
DIST_COMMON = Makefile.am Makefile.in download_pdb_from_NCI.pl.in \
	download_xyz_from_NCI.pl.in
all: all-am

.SUFFIXES:
$(srcdir)/Makefile.in:  Makefile.am  $(top_srcdir)/configure.in $(ACLOCAL_M4)
	cd $(top_srcdir) && \
	  $(AUTOMAKE) --gnu  bin/download/Makefile
Makefile:  $(srcdir)/Makefile.in  $(top_builddir)/config.status
	cd $(top_builddir) && \
	  CONFIG_HEADERS= CONFIG_LINKS= \
	  CONFIG_FILES=$(subdir)/$@ $(SHELL) ./config.status
download_pdb_from_NCI.pl: $(top_builddir)/config.status download_pdb_from_NCI.pl.in
	cd $(top_builddir) && CONFIG_FILES=$(subdir)/$@ CONFIG_HEADERS= CONFIG_LINKS= $(SHELL) ./config.status
download_xyz_from_NCI.pl: $(top_builddir)/config.status download_xyz_from_NCI.pl.in
	cd $(top_builddir) && CONFIG_FILES=$(subdir)/$@ CONFIG_HEADERS= CONFIG_LINKS= $(SHELL) ./config.status
install-binSCRIPTS: $(bin_SCRIPTS)
	@$(NORMAL_INSTALL)
	$(mkinstalldirs) $(DESTDIR)$(bindir)
	@list='$(bin_SCRIPTS)'; for p in $$list; do \
	  f="`echo $$p|sed '$(transform)'`"; \
	  if test -f $$p; then \
	    echo " $(INSTALL_SCRIPT) $$p $(DESTDIR)$(bindir)/$$f"; \
	    $(INSTALL_SCRIPT) $$p $(DESTDIR)$(bindir)/$$f; \
	  elif test -f $(srcdir)/$$p; then \
	    echo " $(INSTALL_SCRIPT) $(srcdir)/$$p $(DESTDIR)$(bindir)/$$f"; \
	    $(INSTALL_SCRIPT) $(srcdir)/$$p $(DESTDIR)$(bindir)/$$f; \
	  else :; fi; \
	done

uninstall-binSCRIPTS:
	@$(NORMAL_UNINSTALL)
	@list='$(bin_SCRIPTS)'; for p in $$list; do \
	  f="`echo $$p|sed '$(transform)'`"; \
	  echo " rm -f $(DESTDIR)$(bindir)/$$f"; \
	  rm -f $(DESTDIR)$(bindir)/$$f; \
	done
uninstall-info-am:
tags: TAGS
TAGS:


DISTFILES = $(DIST_COMMON) $(DIST_SOURCES) $(TEXINFOS) $(EXTRA_DIST)

top_distdir = ../..
distdir = $(top_distdir)/$(PACKAGE)-$(VERSION)

distdir: $(DISTFILES)
	@for file in $(DISTFILES); do \
	  if test -f $$file; then d=.; else d=$(srcdir); fi; \
	  dir=`echo "$$file" | sed -e 's,/[^/]*$$,,'`; \
	  if test "$$dir" != "$$file" && test "$$dir" != "."; then \
	    $(mkinstalldirs) "$(distdir)/$$dir"; \
	  fi; \
	  if test -d $$d/$$file; then \
	    cp -pR $$d/$$file $(distdir) \
	    || exit 1; \
	  else \
	    test -f $(distdir)/$$file \
	    || cp -p $$d/$$file $(distdir)/$$file \
	    || exit 1; \
	  fi; \
	done
check-am: all-am
check: check-am
all-am: Makefile $(SCRIPTS)

installdirs:
	$(mkinstalldirs) $(DESTDIR)$(bindir)

install: install-am
install-exec: install-exec-am
install-data: install-data-am
uninstall: uninstall-am

install-am: all-am
	@$(MAKE) $(AM_MAKEFLAGS) install-exec-am install-data-am

installcheck: installcheck-am
install-strip:
	$(MAKE) $(AM_MAKEFLAGS) INSTALL_PROGRAM="$(INSTALL_STRIP_PROGRAM)" \
	  `test -z '$(STRIP)' || \
	    echo "INSTALL_PROGRAM_ENV=STRIPPROG='$(STRIP)'"` install
mostlyclean-generic:

clean-generic:
	-test -z "$(CLEANFILES)" || rm -f $(CLEANFILES)

distclean-generic:
	-rm -f Makefile $(CONFIG_CLEAN_FILES) stamp-h stamp-h[0-9]*

maintainer-clean-generic:
	@echo "This command is intended for maintainers to use"
	@echo "it deletes files that may require special tools to rebuild."
clean: clean-am

clean-am: clean-generic mostlyclean-am

distclean: distclean-am

distclean-am: clean-am distclean-generic

dvi: dvi-am

dvi-am:

info: info-am

info-am:

install-data-am:

install-exec-am: install-binSCRIPTS

install-info: install-info-am

install-man:

installcheck-am:

maintainer-clean: maintainer-clean-am

maintainer-clean-am: distclean-am maintainer-clean-generic

mostlyclean: mostlyclean-am

mostlyclean-am: mostlyclean-generic

uninstall-am: uninstall-binSCRIPTS uninstall-info-am

.PHONY: all all-am check check-am clean clean-generic distclean \
	distclean-generic distdir dvi dvi-am info info-am install \
	install-am install-binSCRIPTS install-data install-data-am \
	install-exec install-exec-am install-info install-info-am \
	install-man install-strip installcheck installcheck-am \
	installdirs maintainer-clean maintainer-clean-generic \
	mostlyclean mostlyclean-generic uninstall uninstall-am \
	uninstall-binSCRIPTS uninstall-info-am

# Tell versions [3.59,3.63) of GNU make to not export all variables.
# Otherwise a system limit (for SysV at least) may be exceeded.
.NOEXPORT:

--- NEW FILE: download_pdb_from_NCI.pl.in ---
#! @PATHTOPERL@ -w
use diagnostics;
use strict;
use LWP;
use LWP::Simple;
use XML::XPath;

my $root = "../../data/dadml/3d/pdb";
my $urlbase = "http://131.188.127.153/cgi-bin/services/ncidb/ncidb2.tcl";

# Check command line options
if (@ARGV == 0) {
  print "Usage: $0 <xml-files>$/";
  exit;
}

# Global variables
my $nr_downloaded_PDBs = 0;
my $nr_PDB_in_NCI = 0;
my $nr_PDB_already_done = 0;
my $nr_CAS_found = 0;
my $nr_files = scalar @ARGV;

# Loop over all files
my $cas = "";
foreach my $arg (@ARGV) {
    print "Checking $arg...$/";

    my $xp = XML::XPath->new(filename => $arg);
    my $cas = $xp->findvalue('/ITEM/INDEX[@CLASS="CAS-NUMBER"]');
          
    if ($cas ne "" && (!-e "$root/$cas.pdb")) {
	$nr_CAS_found++;
        my $url = "$urlbase?op1=cas&data1=$cas&op2=cas&data2=&op3=inclformula&data3=&op4=fse&data4=&dohighlight=1&andor=and&maxhits=100&timeout=90&output=pdb&sort=nsc";
        print "URL: $url\n";

        my $browser = LWP::UserAgent->new();
        $browser->agent("WOC Downloader");
        my $request = HTTP::Request->new(GET => $url);
        print STDERR "   ...trying to download PDB for $cas";
        my $foo = $browser->request($request);
        if ($foo->is_success) {
            my $content = $foo->content || "";
            if ($content ne "" && !($content =~ /HTML/i)) {
                print " ... and saving$/";
                open (PDBFILE, ">$root/$cas.pdb");
		print PDBFILE $content;              
		$nr_downloaded_PDBs++;
            } else {
                print " ... no PDB file found$/";
                $nr_PDB_in_NCI++;
            }
        } else {
            print " ... unexpected error has occured\n";
        }
        
    } else {
        if ($cas eq "") {
            print " ... no CAS number$/";
        } else {
            print "  ...$cas.pdb already present!$/";
	    $nr_PDB_already_done++;
        }
    }
}

# Print statistics
print     "  ----------------------------$/";
print     "Files checked             : $nr_files$/";
print     "   CAS number found       : $nr_CAS_found$/";
print     "   PDB files downloaded   : $nr_downloaded_PDBs$/";
print     "   PDB files not in NCI   : $nr_PDB_in_NCI$/";
print     "   PDB already done       : $nr_PDB_already_done$/";

--- NEW FILE: download_xyz_from_NCI.pl.in ---
#! @PATHTOPERL@ -w
use diagnostics;
use strict;
use LWP;
use LWP::Simple;

my $root = "../../data/dadml/3d/xyz";
my $urlbase = "http://131.188.127.153/cgi-bin/services/ncidb/ncidb2.tcl";

# Check command line options
if (@ARGV == 0) {
  print "Usage: $0 <xml-files>$/";
  exit;
}

# Global variables
my $no_downloaded_XYZs = 0;
my $no_XYZ_in_NCI = 0;
my $no_XYZ_already_done = 0;
my $no_CAS_found = 0;
my $no_files = scalar @ARGV;

# Loop over all files
my $cas = "";
foreach my $arg (@ARGV) {
    print "Checking $arg...$/";
    open (FILEHANDLE, "<$arg");
    $cas = "";
    while (<FILEHANDLE>) {
        if (/CAS-NUMBER/i && /\>(.+?)\</) {
            $cas = $1;
        }
    };
    if ($cas ne "" && (!-e "$root/$cas.xyz")) {
	$no_CAS_found++;
        my $url = "$urlbase?op1=cas&data1=$cas&op2=cas&data2=&op3=inclformula&data3=&op4=fse&data4=&dohighlight=1&andor=and&maxhits=100&timeout=90&output=xyz&sort=nsc";

        my $browser = LWP::UserAgent->new();
        $browser->agent("WOC Downloader");
        my $request = HTTP::Request->new(GET => $url);
        print STDERR "   ...downloading XYZ for $cas";
        my $foo = $browser->request($request);
        if ($foo->is_success) {
            my $content = $foo->content || "";
            if ($content ne "" && !($content =~ /HTML/i)) {
                print " ... and saving$/";
                open (XYZFILE, ">$root/$cas.xyz");
		print XYZFILE $content;              
		$no_downloaded_XYZs++;
            } else {
                print " ... no XYZ file found$/";
                $no_XYZ_in_NCI++;
            }
        }
    } else {
        if ($cas eq "") {
            print " ... no CAS number$/";
        } else {
            print "  ...$cas.xyz already downloaded!$/";
	    $no_XYZ_already_done++;
        }
    }
}

# Print statistics
print     "  ----------------------------$/";
print     "Files checked             : $no_files$/";
print     "   CAS number found       : $no_CAS_found$/";
print     "   XYZ files downloaded   : $no_downloaded_XYZs$/";
print     "   XYZ files not in NCI   : $no_XYZ_in_NCI$/";
print     "   XYZ already done       : $no_XYZ_already_done$/";