Add a --files option (#1426)

* mlr --files

* doc mods

docs/src/keystroke-savers.md

@@ -87,6 +87,16 @@ If there's more than one input file, you can use `--mfrom`, then however many fi
 <b>mlr --c2p --mfrom data/*.csv -- sort -n index</b>
 </pre>
 
+Alternatively, you may place filenames within another file, one per line:
+
+<pre class="pre-highlight-non-pair">
+<b>cat data/filenames.txt</b>
+</pre>
+
+<pre class="pre-highlight-non-pair">
+<b>mlr --c2p --files data/filenames.txt cat</b>
+</pre>
+
 ## Shortest flags for CSV, TSV, and JSON
 
 The following have even shorter versions:

docs/src/keystroke-savers.md.in

@@ -32,6 +32,16 @@ GENMD-SHOW-COMMAND
 mlr --c2p --mfrom data/*.csv -- sort -n index
 GENMD-EOF
 
+Alternatively, you may place filenames within another file, one per line:
+
+GENMD-SHOW-COMMAND
+cat data/filenames.txt
+GENMD-EOF
+
+GENMD-SHOW-COMMAND
+mlr --c2p --files data/filenames.txt cat
+GENMD-EOF
+
 ## Shortest flags for CSV, TSV, and JSON
 
 The following have even shorter versions:

docs/src/manpage.md

@@ -513,6 +513,9 @@ MILLER(1)                                                            MILLER(1)
                                 large files. Use this flag to force frequent updates
                                 even when output is to a pipe or file, at a
                                 performance cost.
+       --files {filename}       Use this to specify a file which itself contains, one
+                                per line, names of input files. May be used more than
+                                once.
        --from {filename}        Use this to specify an input file before the verb(s),
                                 rather than after. May be used more than once.
                                 Example: `mlr --from a.dat --from b.dat cat` is the
@@ -3645,5 +3648,5 @@ MILLER(1)                                                            MILLER(1)
 
 
 
-                                  2023-11-11                         MILLER(1)
+                                  2023-11-12                         MILLER(1)
 </pre>

docs/src/manpage.txt

@@ -492,6 +492,9 @@ MILLER(1)                                                            MILLER(1)
                                 large files. Use this flag to force frequent updates
                                 even when output is to a pipe or file, at a
                                 performance cost.
+       --files {filename}       Use this to specify a file which itself contains, one
+                                per line, names of input files. May be used more than
+                                once.
        --from {filename}        Use this to specify an input file before the verb(s),
                                 rather than after. May be used more than once.
                                 Example: `mlr --from a.dat --from b.dat cat` is the
@@ -3624,4 +3627,4 @@ MILLER(1)                                                            MILLER(1)
 
 
 
-                                  2023-11-11                         MILLER(1)
+                                  2023-11-12                         MILLER(1)

docs/src/reference-main-flag-list.md

@@ -266,6 +266,7 @@ These are flags which don't fit into any other category.
 **Flags:**
 
 * `--fflush`: Force buffered output to be written after every output record. The default is flush output after every record if the output is to the terminal, or less often if the output is to a file or a pipe. The default is a significant performance optimization for large files.  Use this flag to force frequent updates even when output is to a pipe or file, at a performance cost.
+* `--files {filename}`: Use this to specify a file which itself contains, one per line, names of input files. May be used more than once.
 * `--from {filename}`: Use this to specify an input file before the verb(s), rather than after. May be used more than once. Example: `mlr --from a.dat --from b.dat cat` is the same as `mlr cat a.dat b.dat`.
 * `--hash-records`: This is an internal parameter which normally does not need to be modified. It controls the mechanism by which Miller accesses fields within records. In general --no-hash-records is faster, and is the default. For specific use-cases involving data having many fields, and many of them being processed during a given processing run, --hash-records might offer a slight performance benefit.
 * `--infer-int-as-float or -A`: Cast all integers in data files to floats.

man/manpage.txt

@@ -492,6 +492,9 @@ MILLER(1)                                                            MILLER(1)
                                 large files. Use this flag to force frequent updates
                                 even when output is to a pipe or file, at a
                                 performance cost.
+       --files {filename}       Use this to specify a file which itself contains, one
+                                per line, names of input files. May be used more than
+                                once.
        --from {filename}        Use this to specify an input file before the verb(s),
                                 rather than after. May be used more than once.
                                 Example: `mlr --from a.dat --from b.dat cat` is the
@@ -3624,4 +3627,4 @@ MILLER(1)                                                            MILLER(1)
 
 
 
-                                  2023-11-11                         MILLER(1)
+                                  2023-11-12                         MILLER(1)

man/mlr.1

@@ -611,6 +611,9 @@ These are flags which don't fit into any other category.
                          large files. Use this flag to force frequent updates
                          even when output is to a pipe or file, at a
                          performance cost.
+--files {filename}       Use this to specify a file which itself contains, one
+                         per line, names of input files. May be used more than
+                         once.
 --from {filename}        Use this to specify an input file before the verb(s),
                          rather than after. May be used more than once.
                          Example: `mlr --from a.dat --from b.dat cat` is the

pkg/cli/option_parse.go

@@ -7,7 +7,9 @@
 package cli
 
 import (
+	"bufio"
 	"fmt"
+	"io"
 	"os"
 	"strings"
 
@@ -2797,6 +2799,51 @@ var MiscFlagSection = FlagSection{
 			},
 		},
 
+		{
+			name: "--files",
+			arg:  "{filename}",
+			help: "Use this to specify a file which itself contains, one per line, names of input files. May be used more than once.",
+			parser: func(args []string, argc int, pargi *int, options *TOptions) {
+				CheckArgCount(args, *pargi, argc, 2)
+
+				fileName := args[*pargi+1]
+				handle, err := os.Open(fileName)
+				if err != nil {
+					/// XXXX return false
+					fmt.Fprintln(os.Stderr, "mlr", err)
+					os.Exit(1)
+				}
+				defer handle.Close()
+
+				lineReader := bufio.NewReader(handle)
+
+				eof := false
+				lineno := 0
+				for !eof {
+					line, err := lineReader.ReadString('\n')
+					if err == io.EOF {
+						err = nil
+						eof = true
+						break
+					}
+					lineno++
+
+					if err != nil {
+						fmt.Fprintln(os.Stderr, "mlr", err)
+						os.Exit(1)
+					}
+
+					// This is how to do a chomp:
+					// TODO: handle \r\n with libified solution.
+					line = strings.TrimRight(line, "\n")
+
+					options.FileNames = append(options.FileNames, line)
+				}
+
+				*pargi += 2
+			},
+		},
+
 		{
 			name: "--ofmt",
 			arg:  "{format}",