diff options
| -rw-r--r-- | share/txr/stdlib/awk.tl | 20 | ||||
| -rw-r--r-- | txr.1 | 55 |
2 files changed, 58 insertions, 17 deletions
diff --git a/share/txr/stdlib/awk.tl b/share/txr/stdlib/awk.tl index e74a0a18..62311fe2 100644 --- a/share/txr/stdlib/awk.tl +++ b/share/txr/stdlib/awk.tl @@ -25,7 +25,7 @@ (defstruct sys:awk-state () (rs "\n") - (fs #/[ \t\n]+/) + (fs) (ofs " ") (ors "\n") (inputs (or *args* (list *stdin*))) @@ -52,11 +52,19 @@ (defmeth sys:awk-state rec-to-f (self) (cond ((equal self.rec "") - (set self.fields nil) - (set self.nf 0)) - (t - (set self.fields (split-str self.rec self.fs)) - (set self.nf (length self.fields))))) + (set self.fields nil + self.nf 0)) + (self.fs + (set self.fields (split-str self.rec self.fs) + self.nf (length self.fields))) + ((let ((trimmed (trim-str self.rec))) + (cond + ((equal trimmed "") + (set self.fields nil + self.nf 0)) + (t + (set self.fields (split-str trimmed #/[ \t\n]+/) + self.nf (length self.fields)))))))) (defmeth sys:awk-state f-to-rec (self) (set self.rec (cat-str self.fields self.ofs))) @@ -37618,15 +37618,45 @@ The awk variable specifies a string or regular expression which is used for delimiting records into fields. +The +.code fs +variable is initially +.codn nil . + +If +.code fs +is nil, then, prior to field splitting, leading and trailing +whitespace is trimmed from the value of +.codn rec , +using the +.code trim-str +function. The subsequent field splitting operates on this +trimmed value, which isn't stored back into +.codn rec . + Regardless of the value of .codn fs , -an empty record produces no fields: +a record which is empty (tested after the trimming described above, if that +takes place) produces no fields: .code f is the empty list, and .code nf is zero. -When a record is not empty, matches for the +If +.code fs +is nil, then +In this special case, the splitting is performed using +the regular expression +This means that, by default, fields are separated by one or more consecutive +whitespace characters, which can be any mixture of spaces, tabs or newlines. +Newlines are included because they can occur in a record when the value of the +record separator +.code rs +is customized. + +When a record is not empty, +matches for the .code fs pattern are identified in it, and those matching parts separate fields: the fields are the possibly empty non-matching parts between the matches. @@ -37636,16 +37666,19 @@ If is not found in the record, then the entire record is taken as a single field. -The initial value of +If .code fs -is the regular expression -.codn "#/[ \et\en]+/" . -This means that, by default, fields are separated by one or more consecutive -whitespace characters, which can be any mixture of spaces, tabs or newlines. -Newlines are included because they can occur in a record when the value of the -record separator -.code rs -is customized. +is not +.codn nil , +it must specify a string, or a regular expression. +If it is +.codn nil , +then the regular expression +.code "#/[ \et\en]+/" +is used. A string value of +.code fs +denotes an exact match for that string; it isn't treated +as a regular expression. .coNP Variable @ ofs .desc |