Do not treat isolated CR in input data as new-line.

User "tvw" on IRC reported that PSPP failed to parse data that SPSS 18
accepted.  We found that the problem was carriage return (CR) characters
in the middle of a line.  PSPP treated these as new-lines, but SPSS did
not.  This commit adopts the SPSS behavior in PSPP and adjusts one test
that checks this behavior.

This will break reading some old Mac OS files, since Mac OS before version
10 used CR without LF as new-line.  Time will tell whether this is a real
problem for our users.

diff --git a/src/libpspp/str.c b/src/libpspp/str.c
index 79f3c912e9b649cf39d3ab9a0b37510e25867bf5..71f54474d57f995f8c5b73572e1d8f761b7e934e 100644 (file)
--- a/src/libpspp/str.c
+++ b/src/libpspp/str.c
@@ -1,5 +1,5 @@
 /* PSPP - a program for statistical analysis.
-   Copyright (C) 1997-9, 2000, 2006, 2009 Free Software Foundation, Inc.
+   Copyright (C) 1997-9, 2000, 2006, 2009, 2010 Free Software Foundation, Inc.
 
    This program is free software: you can redistribute it and/or modify
    it under the terms of the GNU General Public License as published by
@@ -1240,9 +1240,9 @@ ds_steal_cstr (struct string *st)
    to ST, false if no characters were read before an I/O error or
    end of file (or if MAX_LENGTH was 0).
 
-   This function accepts LF, CR LF, and CR sequences as new-line,
-   and translates each of them to a single '\n' new-line
-   character in ST. */
+   This function treats LF and CR LF sequences as new-line,
+   translating each of them to a single '\n' new-line character
+   in ST. */
 bool
 ds_read_line (struct string *st, FILE *stream, size_t max_length)
 {
@@ -1251,21 +1251,36 @@ ds_read_line (struct string *st, FILE *stream, size_t max_length)
   for (length = 0; length < max_length; length++)
     {
       int c = getc (stream);
-      if (c == EOF)
-        break;
-
-      if (c == '\r')
+      switch (c)
         {
+        case EOF:
+          return length > 0;
+
+        case '\n':
+          ds_put_char (st, c);
+          return true;
+
+        case '\r':
           c = getc (stream);
-          if (c != '\n')
+          if (c == '\n')
             {
+              /* CR followed by LF is special: translate to \n. */
+              ds_put_char (st, '\n');
+              return true;
+            }
+          else
+            {
+              /* CR followed by anything else is just CR. */
+              ds_put_char (st, '\r');
+              if (c == EOF)
+                return true;
               ungetc (c, stream);
-              c = '\n';
             }
+          break;
+
+        default:
+          ds_put_char (st, c);
         }
-      ds_put_char (st, c);
-      if (c == '\n')
-        return true;
     }
 
   return length > 0;

diff --git a/tests/command/line-ends.sh b/tests/command/line-ends.sh
index 2c12e4f67e851afa75539c8d9608fd527b193a48..7649962979f2700b136510a26e014dc74cc1b119 100755 (executable)
--- a/tests/command/line-ends.sh
+++ b/tests/command/line-ends.sh
@@ -67,7 +67,7 @@ if [ $? -ne 0 ] ; then no_result ; fi
 
 
 activity="create input.txt"
-printf '1 2 3\n4 5 6\r\n7 8 9\r10 11 12\n13 14 15 \r\n16 17 18\r' > input.txt
+printf '1 2 3\n4 5 6\r\n7\r8\r9\r\n10 11 12\n13 14 15 \r\n16\r\r17\r18\n' > input.txt
 if [ $? -ne 0 ] ; then no_result ; fi
 
 
@@ -77,7 +77,7 @@ if [ $? -ne 0 ] ; then no_result ; fi
 activity="check input.txt"
 cksum input.txt > input.cksum
 diff input.cksum - <<EOF
-4116052799 48 input.txt
+1732021750 50 input.txt
 EOF
 if [ $? -ne 0 ] ; then no_result ; fi