diff --git a/c/containers/lrec_parsers.c b/c/containers/lrec_parsers.c
index 3f390fdd5..6d67dcfa6 100644
--- a/c/containers/lrec_parsers.c
+++ b/c/containers/lrec_parsers.c
@@ -174,13 +174,16 @@ lrec_t* lrec_parse_csv(hdr_keeper_t* phdr_keeper, char* data_line, char ifs, int
char* value = data_line;
// xxx needs hdr/data length check!!!!!!
-
// xxx needs pe-non-null (hdr-empty) check:
sllse_t* pe = phdr_keeper->pkeys->phead;
for (char* p = data_line; *p; ) {
if (*p == ifs) {
*p = 0;
+ if (pe == NULL) { // xxx to do: get file-name/line-number context in here
+ fprintf(stderr, "Header-data length mismatch!\n");
+ exit(1);
+ }
key = pe->value;
lrec_put_no_free(prec, key, value);
@@ -195,8 +198,16 @@ lrec_t* lrec_parse_csv(hdr_keeper_t* phdr_keeper, char* data_line, char ifs, int
p++;
}
}
+ if (pe == NULL) {
+ fprintf(stderr, "Header-data length mismatch!\n");
+ exit(1);
+ }
key = pe->value;
lrec_put_no_free(prec, key, value);
+ if (pe->pnext != NULL) {
+ fprintf(stderr, "Header-data length mismatch!\n");
+ exit(1);
+ }
return prec;
}
diff --git a/c/mapping/mapper_check.c b/c/mapping/mapper_check.c
index 82db55aec..06eff30db 100644
--- a/c/mapping/mapper_check.c
+++ b/c/mapping/mapper_check.c
@@ -23,7 +23,7 @@ mapper_t* mapper_check_alloc() {
void mapper_check_usage(char* argv0, char* verb) {
fprintf(stdout, "Usage: %s %s\n", argv0, verb);
fprintf(stdout, "Consumes records without printing any output.\n");
- fprintf(stdout, "Useful for doing a well-formatted check on input data.\n");
+ fprintf(stdout, "Useful for doing a well-formatted check on CSV input data.\n");
}
mapper_t* mapper_check_parse_cli(int* pargi, int argc, char** argv) {
diff --git a/c/todo.txt b/c/todo.txt
index 584aed5a0..d5ce14894 100644
--- a/c/todo.txt
+++ b/c/todo.txt
@@ -2,9 +2,6 @@
! BUGFIXES !
* --ofmt ignored in put. perhaps best to reglobalize.
-* csv hdr/data length check!!
-* echo a|mlr --dkvp --oxtab cat puts 'a a'
-
================================================================
FEATURES
diff --git a/doc/content-for-record-heterogeneity.html b/doc/content-for-record-heterogeneity.html
index 990d06f71..2a89e2585 100644
--- a/doc/content-for-record-heterogeneity.html
+++ b/doc/content-for-record-heterogeneity.html
@@ -22,7 +22,7 @@ POKI_RUN_COMMAND{{mlr --opprint cat data/het.dkvp}}HERE
POKI_PUT_LINK_FOR_PAGE(reference.html)HERE):
|
-POKI_RUN_COMMAND{{mlr --csv group-like data/het.dkvp}}HERE
+POKI_RUN_COMMAND{{mlr --ocsv group-like data/het.dkvp}}HERE
|
POKI_RUN_COMMAND{{mlr --opprint group-like data/het.dkvp}}HERE
|
diff --git a/doc/content-for-reference.html b/doc/content-for-reference.html
index b28b5c68e..45dc9585a 100644
--- a/doc/content-for-reference.html
+++ b/doc/content-for-reference.html
@@ -214,6 +214,11 @@ POKI_RUN_COMMAND{{mlr --csv cat a.csv b.csv}}HERE
POKI_RUN_COMMAND{{mlr --icsv --oxtab cat a.csv b.csv}}HERE
+
+check
+
+POKI_RUN_COMMAND{{mlr check --help}}HERE
+
count-distinct
diff --git a/doc/record-heterogeneity.html b/doc/record-heterogeneity.html
index 20084c10e..a47e798ea 100644
--- a/doc/record-heterogeneity.html
+++ b/doc/record-heterogeneity.html
@@ -173,14 +173,15 @@ resource loadsec ok
-$ mlr --csv group-like data/het.dkvp
-resource=/path/to/file,loadsec=0.45
-record_count=100,resource=/path/to/file
-record_count=150,resource=/path/to/second/file
+$ mlr --ocsv group-like data/het.dkvp
+resource,loadsec,ok
+/path/to/file,0.45,true
+/path/to/second/file,0.32,true
+/some/other/path,0.97,false
-resource=/path/to/file,loadsec=0.45,ok=true
-resource=/path/to/second/file,loadsec=0.32,ok=true
-resource=/some/other/path,loadsec=0.97,ok=false
+record_count,resource
+100,/path/to/file
+150,/path/to/second/file
diff --git a/doc/reference.html b/doc/reference.html
index 5f4aa9c08..2857c8178 100644
--- a/doc/reference.html
+++ b/doc/reference.html
@@ -99,6 +99,7 @@ Miller commands were run with pretty-print-tabular output format.
• Number formatting
• Data transformations
• cat
+ • check
• count-distinct
• cut
• filter
@@ -468,6 +469,20 @@ c 9
+
+check
+
+
+
+
+$ mlr check --help
+Usage: mlr check
+Consumes records without printing any output.
+Useful for doing a well-formatted check on CSV input data.
+
+
count-distinct
@@ -605,7 +620,7 @@ i j k
$ mlr filter 'FNR == 2' data/small*
a=eks,b=pan,i=2,x=0.7586799647899636,y=0.5221511083334797
-pan=pan,1=1,0.3467901443380824=0.3467901443380824,0.7268028627434533=0.7268028627434533
+1=pan,2=pan,3=1,4=0.3467901443380824,5=0.7268028627434533
a=wye,b=eks,i=10000,x=0.734806020620654365,y=0.884788571337605134