X-Git-Url: https://pintos-os.org/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=src%2Flanguage%2Fdata-io%2Fdata-reader.c;h=6f620a6a948341a0dfa5db150763d20f51e92284;hb=48d85ad2926b978fe73bd754a5baf626881e1915;hp=e3ef8ca15be6b841de239d6d578501b5c7d26b47;hpb=d0371553a98cd169353bf6d211e375e5ffc3a3bd;p=pspp-builds.git diff --git a/src/language/data-io/data-reader.c b/src/language/data-io/data-reader.c index e3ef8ca1..6f620a6a 100644 --- a/src/language/data-io/data-reader.c +++ b/src/language/data-io/data-reader.c @@ -23,6 +23,7 @@ #include #include #include +#include #include #include @@ -63,6 +64,7 @@ struct dfm_reader struct string scratch; /* Extra line buffer. */ enum dfm_reader_flags flags; /* Zero or more of DFM_*. */ FILE *file; /* Associated file. */ + off_t file_size; /* File size, or -1 if unavailable. */ size_t pos; /* Offset in line of current character. */ unsigned eof_cnt; /* # of attempts to advance past EOF. */ struct lexer *lexer; /* The lexer reading the file */ @@ -137,6 +139,7 @@ dfm_open_reader (struct file_handle *fh, struct lexer *lexer) r->block_left = 0; if (fh_get_referent (fh) != FH_REF_INLINE) { + struct stat s; r->where.file_name = fh_get_file_name (fh); r->where.line_number = 0; r->file = fn_open (fh_get_file_name (fh), @@ -150,7 +153,10 @@ dfm_open_reader (struct file_handle *fh, struct lexer *lexer) free (r); return NULL; } + r->file_size = fstat (fileno (r->file), &s) == 0 ? s.st_size : -1; } + else + r->file_size = -1; fh_lock_set_aux (lock, r); return r; @@ -181,6 +187,7 @@ read_inline_record (struct dfm_reader *r) if (!lex_get_line_raw (r->lexer)) { + lex_discard_line (r->lexer); msg (SE, _("Unexpected end-of-file while reading data in BEGIN " "DATA. This probably indicates " "a missing or misformatted END DATA command. " @@ -334,7 +341,7 @@ read_file_record (struct dfm_reader *r) switch (fh_get_mode (r->fh)) { case FH_MODE_TEXT: - if (ds_read_line (&r->line, r->file)) + if (ds_read_line (&r->line, r->file, SIZE_MAX)) { ds_chomp (&r->line, '\n'); return true; @@ -590,12 +597,33 @@ dfm_expand_tabs (struct dfm_reader *r) } /* Returns the legacy character encoding of data read from READER. */ -enum legacy_encoding +const char * dfm_reader_get_legacy_encoding (const struct dfm_reader *reader) { return fh_get_legacy_encoding (reader->fh); } +/* Returns a number between 0 and 100 that approximates the + percentage of the data in READER that has already been read, + or -1 if this value cannot be estimated. + + ftello is slow in glibc (it flushes the read buffer), so don't + call this function unless you need to. */ +int +dfm_get_percent_read (const struct dfm_reader *reader) +{ + if (reader->file_size >= 0) + { + off_t position = ftello (reader->file); + if (position >= 0) + { + double p = 100.0 * position / reader->file_size; + return p < 0 ? 0 : p > 100 ? 100 : p; + } + } + return -1; +} + /* Causes dfm_get_record() or dfm_get_whole_record() to read in the next record the next time it is executed on file HANDLE. */