Allow '-' to mean read from stdin.

[ocaml-csv.git] / csvtool.ml

diff --git a/csvtool.ml b/csvtool.ml
index edfaedd..d944160 100644 (file)
--- a/csvtool.ml
+++ b/csvtool.ml
@@ -1,5 +1,5 @@
 (* Handy tool for managing CSV files.
 (* Handy tool for managing CSV files.

- * $Id: csvtool.ml,v 1.6 2006-11-24 10:09:56 rich Exp $
+ * $Id: csvtool.ml,v 1.8 2006-11-24 15:49:24 rich Exp $

  *)
 
 open Printf
  *)
 
 open Printf


@@ -153,6 +153,14 @@ let cmd_namedcols ~input_sep ~output_sep ~chan names files =
        match csv with
        | [] -> failwith "no rows in this CSV file"
        | h :: t -> h, t in
        match csv with
        | [] -> failwith "no rows in this CSV file"
        | h :: t -> h, t in

+      (* Do the headers requested exist in the CSV file?  If not,
+       * throw an error.
+       *)
+      List.iter (
+        fun name ->
+         if not (List.mem name header) then
+           failwith ("namedcol: requested header not in CSV file: " ^ name)
+      ) names;

       let data = associate header data in
       let data = List.map (
        fun row -> List.map (fun name -> List.assoc name row) names
       let data = associate header data in
       let data = List.map (
        fun row -> List.map (fun name -> List.assoc name row) names


@@ -189,9 +197,76 @@ let cmd_cat ~input_sep ~output_sep ~chan files =
   in
   List.iter (
     fun filename ->
   in
   List.iter (
     fun filename ->

-      let in_chan = open_in filename in
+      let in_chan, close =
+       match filename with
+       | "-" -> stdin, false
+       | filename -> open_in filename, true in
+      load_rows ~separator:input_sep f in_chan;
+      if close then close_in in_chan
+  ) files
+
+let cmd_set_columns ~input_sep ~output_sep ~chan cols files =
+  (* Avoid loading the whole file into memory. *)
+  let f row =
+    let csv = [row] in
+    let csv = set_columns cols csv in
+    save_out ~separator:output_sep chan csv
+  in
+  List.iter (
+    fun filename ->
+      let in_chan, close =
+       match filename with
+       | "-" -> stdin, false
+       | filename -> open_in filename, true in
+      load_rows ~separator:input_sep f in_chan;
+      if close then close_in in_chan
+  ) files
+
+let cmd_set_rows ~input_sep ~output_sep ~chan rows files =
+  let csv = List.concat (List.map (load ~separator:input_sep) files) in
+  let csv = set_rows rows csv in
+  save_out ~separator:output_sep chan csv
+
+let cmd_head ~input_sep ~output_sep ~chan rows files =
+  (* Avoid loading the whole file into memory, or even loading
+   * later files.
+   *)
+  let nr_rows = ref rows in
+  let f row =
+    if !nr_rows > 0 then (
+      decr nr_rows;
+      save_out ~separator:output_sep chan [row]
+    )
+  in
+  List.iter (
+    fun filename ->
+      if !nr_rows > 0 then (
+        let in_chan, close =
+         match filename with
+         | "-" -> stdin, false
+         | filename -> open_in filename, true in
+       load_rows ~separator:input_sep f in_chan;
+       if close then close_in in_chan
+      )
+  ) files
+
+let cmd_drop ~input_sep ~output_sep ~chan rows files =
+  (* Avoid loading the whole file into memory. *)
+  let nr_rows = ref rows in
+  let f row =
+    if !nr_rows = 0 then
+      save_out ~separator:output_sep chan [row]
+    else
+      decr nr_rows
+  in
+  List.iter (
+    fun filename ->
+      let in_chan, close =
+       match filename with
+       | "-" -> stdin, false
+       | filename -> open_in filename, true in

       load_rows ~separator:input_sep f in_chan;
       load_rows ~separator:input_sep f in_chan;

-      close_in in_chan
+      if close then close_in in_chan

   ) files
 
 let cmd_square ~input_sep ~output_sep ~chan files =
   ) files
 
 let cmd_square ~input_sep ~output_sep ~chan files =


@@ -321,14 +396,39 @@ Commands:
   height
     Print the number of rows in the CSV file.
 
   height
     Print the number of rows in the CSV file.
 

-  readable
-    Print the input CSV in a readable format.
+    For most CSV files this is equivalent to 'wc -l', but note that
+    some CSV files can contain a row which breaks over two (or more)
+    lines.
+
+  setcolumns cols
+    Set the number of columns to cols (this also makes the CSV file
+    square).  Any short rows are padding with blank cells.  Any
+    long rows are truncated.
+
+  setrows rows
+    'setrows n' sets the number of rows to 'n'.  If there are fewer
+    than 'n' rows in the CSV files, then empty blank lines are added.
+
+  head rows
+  take rows
+    'head n' and 'take n' (which are synonyms) take the first 'n'
+    rows.  If there are fewer than 'n' rows, padding is not added.
+
+  drop rows
+    Drop the first 'rows' rows and return the rest (if any).
+
+      Example:
+        To remove the headings from a CSV file with headings:
+          csvtool drop 1 input.csv > output.csv
+
+        To extract rows 11 through 20 from a file:
+          csvtool drop 10 input.csv | csvtool take 10 - > output.csv

 
   cat
     This concatenates the input files together and writes them to
     the output.  You can use this to change the separator character.
 
 
   cat
     This concatenates the input files together and writes them to
     the output.  You can use this to change the separator character.
 

-      Example: csvtool -t TAB -u , cat input.tsv > output.csv
+      Example: csvtool -t TAB -u COMMA cat input.tsv > output.csv

 
   join <column-spec1> <column-spec2>
     Join (collate) multiple CSV files together.
 
   join <column-spec1> <column-spec2>
     Join (collate) multiple CSV files together.


@@ -338,7 +438,7 @@ Commands:
     <column-spec2> controls which columns are copied into the new file.
 
       Example:
     <column-spec2> controls which columns are copied into the new file.
 
       Example:

-        csvtool join 1 2 coll1.csv coll2.csv
+        csvtool join 1 2 coll1.csv coll2.csv > output.csv

         If coll1.csv contains:
           Computers,$40
           Software,$100
         If coll1.csv contains:
           Computers,$40
           Software,$100


@@ -351,9 +451,12 @@ Commands:
   square
     Make the CSV square, so all rows have the same length.
 
   square
     Make the CSV square, so all rows have the same length.
 

+      Example: csvtool square input.csv > input-square.csv
+

   sub r c rows cols
   sub r c rows cols

-    Take a square subset of the CSV, top left at row r, column c (counting
-    from 0), which is rows deep and cols wide.
+    Take a square subset of the CSV, top left at row r, column c, which
+    is rows deep and cols wide.  'r' and 'c' count from 1, or
+    from 0 if -z option is given.

 
   replace <column-spec> update.csv original.csv
     Replace rows in original.csv with rows from update.csv.  The columns
 
   replace <column-spec> update.csv original.csv
     Replace rows in original.csv with rows from update.csv.  The columns


@@ -364,6 +467,9 @@ Commands:
         csvtool replace 3 updates.csv original.csv > new.csv
         mv new.csv original.csv
 
         csvtool replace 3 updates.csv original.csv > new.csv
         mv new.csv original.csv
 

+  readable
+    Print the input CSV in a readable format.
+

 Column specs:
   A <column-spec> is a comma-separated list of column numbers
   or column ranges.
 Column specs:
   A <column-spec> is a comma-separated list of column numbers
   or column ranges.


@@ -379,6 +485,8 @@ Column specs:
 Input files:
   csvtool takes a list of input file(s) from the command line.
 
 Input files:
   csvtool takes a list of input file(s) from the command line.
 

+  If an input filename is '-' then take input from stdin.
+

 Output file:
   Normally the output is written to stdout.  Use the -o option
   to override this.
 Output file:
   Normally the output is written to stdout.  Use the -o option
   to override this.


@@ -413,6 +521,11 @@ let () =
 
   let output_file = ref "" in
 
 
   let output_file = ref "" in
 

+  let rest = ref [] in
+  let set_rest str =
+    rest := str :: !rest
+  in
+

   let argspec = [
     "-t", Arg.String set_input_sep,
     "Input separator char.  Use -t TAB for tab separated input.";
   let argspec = [
     "-t", Arg.String set_input_sep,
     "Input separator char.  Use -t TAB for tab separated input.";


@@ -422,13 +535,10 @@ let () =
     "Write output to file (instead of stdout)";
     "-z", Arg.Set count_zero,
     "Number columns from 0 instead of 1";
     "Write output to file (instead of stdout)";
     "-z", Arg.Set count_zero,
     "Number columns from 0 instead of 1";

+    "-", Arg.Unit (fun () -> set_rest "-"),
+    "" (* Hack to allow '-' for input from stdin. *)

   ] in
 
   ] in
 

-  let rest = ref [] in
-  let set_rest str =
-    rest := str :: !rest
-  in
-

   Arg.parse argspec set_rest usage;
 
   let input_sep = !input_sep in
   Arg.parse argspec set_rest usage;
 
   let input_sep = !input_sep in


@@ -449,9 +559,9 @@ let () =
      | ("namedcol"|"namedcols") :: names :: files ->
         let names = nsplit names "," in
         cmd_namedcols ~input_sep ~output_sep ~chan names files
      | ("namedcol"|"namedcols") :: names :: files ->
         let names = nsplit names "," in
         cmd_namedcols ~input_sep ~output_sep ~chan names files

-     | "width" :: files ->
+     | ("width"|"columns") :: files ->

         cmd_width ~input_sep ~chan files
         cmd_width ~input_sep ~chan files

-     | "height" :: files ->
+     | ("height"|"rows") :: files ->

         cmd_height ~input_sep ~chan files
      | "readable" :: files ->
         cmd_readable ~input_sep ~chan files
         cmd_height ~input_sep ~chan files
      | "readable" :: files ->
         cmd_readable ~input_sep ~chan files


@@ -465,13 +575,28 @@ let () =
         cmd_square ~input_sep ~output_sep ~chan files
      | "sub" :: r :: c :: rows :: cols :: files ->
         let r = int_of_string r in
         cmd_square ~input_sep ~output_sep ~chan files
      | "sub" :: r :: c :: rows :: cols :: files ->
         let r = int_of_string r in

+        let r = if not count_zero then r-1 else r in

         let c = int_of_string c in
         let c = int_of_string c in

+        let c = if not count_zero then c-1 else c in

         let rows = int_of_string rows in
         let cols = int_of_string cols in
         cmd_sub ~input_sep ~output_sep ~chan r c rows cols files
      | "replace" :: colspec :: update :: files ->
         let colspec = parse_colspec ~count_zero colspec in
         cmd_replace ~input_sep ~output_sep ~chan colspec update files
         let rows = int_of_string rows in
         let cols = int_of_string cols in
         cmd_sub ~input_sep ~output_sep ~chan r c rows cols files
      | "replace" :: colspec :: update :: files ->
         let colspec = parse_colspec ~count_zero colspec in
         cmd_replace ~input_sep ~output_sep ~chan colspec update files

+     | ("setcolumns"|"set_columns"|"set-columns"|
+           "setcols"|"set_cols"|"set-cols") :: cols :: files ->
+        let cols = int_of_string cols in
+        cmd_set_columns ~input_sep ~output_sep ~chan cols files
+     | ("setrows"|"set_rows"|"set-rows") :: rows :: files ->
+        let rows = int_of_string rows in
+        cmd_set_rows ~input_sep ~output_sep ~chan rows files
+     | ("head"|"take") :: rows :: files ->
+        let rows = int_of_string rows in
+        cmd_head ~input_sep ~output_sep ~chan rows files
+     | "drop" :: rows :: files ->
+        let rows = int_of_string rows in
+        cmd_drop ~input_sep ~output_sep ~chan rows files

      | _ ->
         prerr_endline (Sys.executable_name ^ " --help for usage");
         exit 2
      | _ ->
         prerr_endline (Sys.executable_name ^ " --help for usage");
         exit 2