add file parser for issue #41

README.md

@@ -93,6 +93,7 @@ The JSON output can be compact (default) or pretty formatted with the `-p` optio
 - `--dig` enables the `dig` command parser
 - `--du` enables the `du` command parser
 - `--env` enables the `env` command parser
+- `--file` enables the `file` command parser
 - `--free` enables the `free` command parser
 - `--fstab` enables the `/etc/fstab` file parser
 - `--group` enables the `/etc/group` file parser
@@ -761,6 +762,41 @@ $ env | jc --env -p          # or:  jc -p env
   ...
 ]
 ```
+### file
+```
+$ file * | jc --file -p
+[
+  {
+    "filename": "Applications",
+    "type": "directory"
+  },
+  {
+    "filename": "another file with spaces",
+    "type": "empty"
+  },
+  {
+    "filename": "argstest.py",
+    "type": "Python script text executable, ASCII text"
+  },
+  {
+    "filename": "blkid-p.out",
+    "type": "ASCII text"
+  },
+  {
+    "filename": "blkid-pi.out",
+    "type": "ASCII text, with very long lines"
+  },
+  {
+    "filename": "cd_catalog.xml",
+    "type": "XML 1.0 document text, ASCII text, with CRLF line terminators"
+  },
+  {
+    "filename": "centosserial.sh",
+    "type": "Bourne-Again shell script text executable, UTF-8 Unicode text"
+  },
+  ...
+]
+```
 ### free
 ```
 $ free | jc --free -p          # or:  jc -p free

changelog.txt

@@ -4,9 +4,12 @@ jc changelog
 - Added ntpq command parser
 - Added timedatectl status command parser
 - Added airport -I and airport -s command parser
+- Added file command parser
+- Optimized history command parser by https://github.com/philippeitis
+- Magic syntax fix for certain edge cases
 
 20200308 v1.8.1
-- CLI and history parser optimizations by https://github.com/philippeitis
+- CLI optimizations by https://github.com/philippeitis
 - Refactored magic syntax function and added tests (https://github.com/philippeitis)
 - Github actions for CI testing on multiple platforms by https://github.com/philippeitis
 - Updated ls parser to fix parsing error in OSX with -lR when there are empty folders

docgen.sh

@@ -15,6 +15,7 @@ pydocmd simple jc.parsers.df+ > ../docs/parsers/df.md
 pydocmd simple jc.parsers.dig+ > ../docs/parsers/dig.md
 pydocmd simple jc.parsers.du+ > ../docs/parsers/du.md
 pydocmd simple jc.parsers.env+ > ../docs/parsers/env.md
+pydocmd simple jc.parsers.file+ > ../docs/parsers/file.md
 pydocmd simple jc.parsers.free+ > ../docs/parsers/free.md
 pydocmd simple jc.parsers.fstab+ > ../docs/parsers/fstab.md
 pydocmd simple jc.parsers.group+ > ../docs/parsers/group.md

docs/parsers/file.md

@@ -0,0 +1,90 @@
+# jc.parsers.file
+jc - JSON CLI output utility file command Parser
+
+Usage:
+
+    specify --file as the first argument if the piped input is coming from file.
+
+Compatibility:
+
+    'linux', 'aix', 'freebsd', 'darwin'
+
+Examples:
+
+    $ file * | jc --file -p
+    [
+      {
+        "filename": "Applications",
+        "type": "directory"
+      },
+      {
+        "filename": "another file with spaces",
+        "type": "empty"
+      },
+      {
+        "filename": "argstest.py",
+        "type": "Python script text executable, ASCII text"
+      },
+      {
+        "filename": "blkid-p.out",
+        "type": "ASCII text"
+      },
+      {
+        "filename": "blkid-pi.out",
+        "type": "ASCII text, with very long lines"
+      },
+      {
+        "filename": "cd_catalog.xml",
+        "type": "XML 1.0 document text, ASCII text, with CRLF line terminators"
+      },
+      {
+        "filename": "centosserial.sh",
+        "type": "Bourne-Again shell script text executable, UTF-8 Unicode text"
+      },
+      ...
+    ]
+
+## info
+```python
+info(self, /, *args, **kwargs)
+```
+
+## process
+```python
+process(proc_data)
+```
+
+Final processing to conform to the schema.
+
+Parameters:
+
+    proc_data:   (dictionary) raw structured data to process
+
+Returns:
+
+    List of dictionaries. Structured data with the following schema:
+
+    [
+      {
+        "filename":   string,
+        "type   ":    string
+      }
+    ]
+
+## parse
+```python
+parse(data, raw=False, quiet=False)
+```
+
+Main text parsing function
+
+Parameters:
+
+    data:        (string)  text data to parse
+    raw:         (boolean) output preprocessed JSON if True
+    quiet:       (boolean) suppress warning messages if True
+
+Returns:
+
+    List of dictionaries. Raw or processed structured data.
+

jc/cli.py

@@ -33,6 +33,7 @@ parsers = [
     'dig',
     'du',
     'env',
+    'file',
     'free',
     'fstab',
     'group',

jc/parsers/file.py

@@ -0,0 +1,128 @@
+"""jc - JSON CLI output utility file command Parser
+
+Usage:
+
+    specify --file as the first argument if the piped input is coming from file.
+
+Compatibility:
+
+    'linux', 'aix', 'freebsd', 'darwin'
+
+Examples:
+
+    $ file * | jc --file -p
+    [
+      {
+        "filename": "Applications",
+        "type": "directory"
+      },
+      {
+        "filename": "another file with spaces",
+        "type": "empty"
+      },
+      {
+        "filename": "argstest.py",
+        "type": "Python script text executable, ASCII text"
+      },
+      {
+        "filename": "blkid-p.out",
+        "type": "ASCII text"
+      },
+      {
+        "filename": "blkid-pi.out",
+        "type": "ASCII text, with very long lines"
+      },
+      {
+        "filename": "cd_catalog.xml",
+        "type": "XML 1.0 document text, ASCII text, with CRLF line terminators"
+      },
+      {
+        "filename": "centosserial.sh",
+        "type": "Bourne-Again shell script text executable, UTF-8 Unicode text"
+      },
+      ...
+    ]
+"""
+import jc.utils
+import jc.parsers.universal
+
+
+class info():
+    version = '1.0'
+    description = 'file command parser'
+    author = 'Kelly Brazil'
+    author_email = 'kellyjonbrazil@gmail.com'
+
+    # compatible options: linux, darwin, cygwin, win32, aix, freebsd
+    compatible = ['linux', 'aix', 'freebsd', 'darwin']
+    magic_commands = ['file']
+
+
+__version__ = info.version
+
+
+def process(proc_data):
+    """
+    Final processing to conform to the schema.
+
+    Parameters:
+
+        proc_data:   (dictionary) raw structured data to process
+
+    Returns:
+
+        List of dictionaries. Structured data with the following schema:
+
+        [
+          {
+            "filename":   string,
+            "type   ":    string
+          }
+        ]
+    """
+    # No further processing
+    return proc_data
+
+
+def parse(data, raw=False, quiet=False):
+    """
+    Main text parsing function
+
+    Parameters:
+
+        data:        (string)  text data to parse
+        raw:         (boolean) output preprocessed JSON if True
+        quiet:       (boolean) suppress warning messages if True
+
+    Returns:
+
+        List of dictionaries. Raw or processed structured data.
+    """
+    if not quiet:
+        jc.utils.compatibility(__name__, info.compatible)
+
+    raw_output = []
+
+    warned = False
+    for line in filter(None, data.splitlines()):
+        linedata = line.rsplit(':', maxsplit=1)
+
+        try:
+            filename = linedata[0].strip()
+            filetype = linedata[1].strip()
+
+            raw_output.append(
+                {
+                    'filename': filename,
+                    'type': filetype
+                }
+            )
+        except IndexError:
+            if not warned:
+                jc.utils.warning_message('Filenames with newline characters detected. Some filenames may be truncated.')
+                warned = True
+
+    if raw:
+        return raw_output
+    else:
+        return process(raw_output)