feat: handle multiple files, closes #5

should worked with globbed usage in shells that expand globs now
like 'marcgrep --count *.mrc'
to do this had to rework the CLI function a bit
but also the output of the count command since printing a bunch of
numbers with no labels isn't helpful, we should see how many records
matched _in each file_ like grep or other tools do
that required rewriting a number of the CLI tests

Author: phette23

marcgrep/cli.py

@@ -1,15 +1,16 @@
-from typing import BinaryIO
+import sys
+from typing import IO, BinaryIO, List, Union
 
 import click
-from pymarc import MARCReader
+from pymarc import Any, MARCReader
 
 from .color import color_field, color_record
 from .filter import Filter
 
 
 @click.command(help="Find MARC records matching patterns in a file.")
 @click.help_option("-h", "--help")
-@click.argument("file", type=click.File("rb"), default="-")
+@click.argument("files", type=click.File("rb"), nargs=-1)
 @click.option("--count", "-c", help="Count matching records", is_flag=True)
 @click.option(
     "--include", "-i", help="Include matching records (repeatable)", multiple=True
@@ -22,47 +23,57 @@
 @click.option("--color", help="Colorize mnemonic MARC output", is_flag=True)
 @click.version_option(package_name="marcgrep", message="%(prog)s %(version)s")
 def main(
-    file: BinaryIO,
+    files: List[BinaryIO],
     color: bool,
     count: bool,
     include: list[str],
     exclude: list[str],
     fields: str,
     limit: int,
 ):
-    counter = 0
-    matched_records = 0
-    reader = MARCReader(file)
+    # handle stdin if no files are provided
+    if not files:
+        files = [sys.stdin.buffer]
 
-    # build a list of filters, start with exclusive because they rule out records quicker
-    filters: list[Filter] = [Filter(pattern, inclusive=False) for pattern in exclude]
-    filters.extend(Filter(pattern) for pattern in include)
+    any_matches = False
 
-    for record in reader:
-        if record:
-            counter += 1
-            if all(f.match(record) for f in filters):
-                matched_records += 1
-                if not count:
-                    if fields:
-                        for f in record.get_fields(*fields.split(",")):
+    for file in files:
+        counter = 0
+        matched_records = 0
+        reader = MARCReader(file)
+
+        # build a list of filters, start with exclusive because they rule out records quicker
+        filters: list[Filter] = [
+            Filter(pattern, inclusive=False) for pattern in exclude
+        ]
+        filters.extend(Filter(pattern) for pattern in include)
+
+        for record in reader:
+            if record:
+                counter += 1
+                if all(f.match(record) for f in filters):
+                    any_matches = True
+                    matched_records += 1
+                    if not count:
+                        if fields:
+                            for f in record.get_fields(*fields.split(",")):
+                                if color:
+                                    color_field(f)
+                                else:
+                                    print(f)
+                        else:
                             if color:
-                                color_field(f)
+                                color_record(record)
                             else:
-                                print(f)
-                    else:
-                        if color:
-                            color_record(record)
-                        else:
-                            print(record)
-            if limit and counter >= limit:
-                break
+                                print(record)
+                if limit and counter >= limit:
+                    break
 
-    if count:
-        print(matched_records)
+        if count:
+            print(f"{file.name}: {matched_records}")
 
     # non-zero exit if no records match
-    return exit(0 if matched_records else 1)
+    return exit(0 if any_matches else 1)
 
 
 if __name__ == "__main__":

readme.md

@@ -16,8 +16,8 @@ pip install marcgrep # or use pip/pip3
 ## Usage
 
 ```sh
-# general command format
-marcgrep OPTIONS FILE.mrc
+# general command format - pass one or more files or pipe stdin
+marcgrep OPTIONS FILE1.mrc FILE2.mrc
 cat FILE.mrc | marcgrep OPTIONS
 # full usage information
 marcgrep -h

test/test_cli.py

@@ -17,13 +17,13 @@ def test_count(self):
         runner = CliRunner()
         result = runner.invoke(main, [ONE_RECORD, "--count"])
         assert result.exit_code == 0
-        assert result.output == "1\n"
+        assert result.output == f"{ONE_RECORD}: 1\n"
         result = runner.invoke(main, [PLAIN_TEXT, "-c"])
         assert result.exit_code == 1
-        assert result.output == "0\n"
+        assert result.output == f"{PLAIN_TEXT}: 0\n"
         result = runner.invoke(main, [OAPEN, "-c"])
         assert result.exit_code == 0
-        assert result.output == "500\n"
+        assert result.output == f"{OAPEN}: 500\n"
 
     def test_print(self):
         runner = CliRunner()
@@ -162,4 +162,21 @@ def test_limit(self, input, expected):
             main, [OAPEN, "--limit", input, "-c", "--include", "245"]
         )
         assert result.exit_code == 0
-        assert result.output == f"{expected}\n"
+        assert result.output == f"{OAPEN}: {expected}\n"
+
+    def test_glob(self):
+        runner = CliRunner()
+        result = runner.invoke(
+            main,
+            ["--count", OAPEN, ONE_RECORD],
+        )
+        assert result.exit_code == 0
+        assert result.output == f"{OAPEN}: 500\n{ONE_RECORD}: 1\n"
+        # should still work with stdin
+        result = runner.invoke(
+            main,
+            ["-f", "245", "-"],
+            input=open(ONE_RECORD, "rb").read(),
+        )
+        assert result.exit_code == 0
+        assert len(result.output.splitlines()) == 1