add slurp functionality

CHANGELOG

@@ -1,13 +1,19 @@
 jc changelog
 
-20231222 v1.24.1
+20240103 v1.24.1
 - Add `kv-dup` parser for Key/Value files with duplicate keys
+- TODO: Add `path-list` string parser to parse path list strings found in env variables
+- Add `--slurp` functionality to wrap output from multiple lines into a single array.
+  Note, this only works with single-line input parsers. (e.g. `date`, `ip-address`, `url`, etc.)
+  Streaming parsers are not supported. Use `jc -hhh` to find parsers compatible with the slurp option.
 - Enhance `proc-net-tcp` parser to add opposite endian support for architectures
   like the s390x
 - Enhance `url` parser to add `parent`, `filename`, `stem`, and `extension` fields
 - Fix `ini` and `ini-dup` parsers to consistently handle null values as empty strings
 - Add source link to online parser documentation
 - Refactor parser aliases for `kv`, `pkg_index_deb`, `lsb_release`, and `os-release`
+- TODO: Add `line_slice` function to `utils.py`
+- TODO: Update copyright date
 
 20231216 v1.24.0
 - Add `debconf-show` command parser

jc/__init__.py

@@ -131,6 +131,7 @@ from .lib import (
     plugin_parser_mod_list as plugin_parser_mod_list,
     standard_parser_mod_list as standard_parser_mod_list,
     streaming_parser_mod_list as streaming_parser_mod_list,
+    slurpable_parser_mod_list as slurpable_parser_mod_list,
     parser_info as parser_info,
     all_parser_info as all_parser_info,
     get_help as get_help

jc/cli.py

@@ -15,7 +15,8 @@ from typing import List, Dict, Iterable, Union, Optional, TextIO
 from types import ModuleType
 from .lib import (
     __version__, parser_info, all_parser_info, parsers, _get_parser, _parser_is_streaming,
-    parser_mod_list, standard_parser_mod_list, plugin_parser_mod_list, streaming_parser_mod_list
+    parser_mod_list, standard_parser_mod_list, plugin_parser_mod_list, streaming_parser_mod_list,
+    slurpable_parser_mod_list, _parser_is_slurpable
 )
 from .jc_types import JSONDictType, CustomColorType, ParserInfoType
 from . import utils
@@ -72,7 +73,7 @@ class JcCli():
         'data_in', 'data_out', 'options', 'args', 'parser_module', 'parser_name', 'indent', 'pad',
         'custom_colors', 'show_hidden', 'show_categories', 'ascii_only', 'json_separators',
         'json_indent', 'run_timestamp', 'about', 'debug', 'verbose_debug', 'force_color', 'mono',
-        'help_me', 'pretty', 'quiet', 'ignore_exceptions', 'raw', 'meta_out', 'unbuffer',
+        'help_me', 'pretty', 'quiet', 'ignore_exceptions', 'raw', 'slurp', 'meta_out', 'unbuffer',
         'version_info', 'yaml_output', 'bash_comp', 'zsh_comp', 'magic_found_parser',
         'magic_options', 'magic_run_command', 'magic_run_command_str', 'magic_stdout',
         'magic_stderr', 'magic_returncode', 'slice_str', 'slice_start', 'slice_end'
@@ -111,6 +112,7 @@ class JcCli():
         self.quiet: bool = False
         self.ignore_exceptions: bool = False
         self.raw: bool = False
+        self.slurp: bool = False
         self.meta_out: bool = False
         self.unbuffer: bool = False
         self.version_info: bool = False
@@ -219,6 +221,7 @@ class JcCli():
         generic = [{'arg': x['argument'], 'desc': x['description']} for x in all_parsers if 'generic' in x.get('tags', [])]
         standard = [{'arg': x['argument'], 'desc': x['description']} for x in all_parsers if 'standard' in x.get('tags', [])]
         command = [{'arg': x['argument'], 'desc': x['description']} for x in all_parsers if 'command' in x.get('tags', [])]
+        slurpable = [{'arg': x['argument'], 'desc': x['description']} for x in all_parsers if 'slurpable' in x.get('tags', [])]
         file_str_bin = [
             {'arg': x['argument'], 'desc': x['description']} for x in all_parsers
                 if 'file' in x.get('tags', []) or
@@ -230,6 +233,7 @@ class JcCli():
             'Generic Parsers:': generic,
             'Standard Spec Parsers:': standard,
             'File/String/Binary Parsers:': file_str_bin,
+            'Slurpable Parsers:': slurpable,
             'Streaming Parsers:': streaming,
             'Command Parsers:': command
         }
@@ -694,6 +698,41 @@ class JcCli():
                 elif self.data_in:
                     self.data_in = list(self.data_in)[self.slice_start:self.slice_end]
 
+    def create_slurp_output(self) -> None:
+        """Slurp output into an array. Only works for single-line strings."""
+        if self.parser_module and not _parser_is_slurpable(self.parser_module):
+            utils.error_message([
+                f'Slurp option not available with the {self.parser_name} parser.'
+            ])
+            self.exit_error()
+
+        if self.parser_module and isinstance(self.data_in, str):
+            self.data_out = []
+            for line in self.data_in.splitlines():
+                parsed_line = self.parser_module.parse(
+                    line,
+                    raw=self.raw,
+                    quiet=self.quiet
+                )
+                self.data_out.append(parsed_line)
+
+            if self.meta_out:
+                self.run_timestamp = datetime.now(timezone.utc)
+                self.add_metadata_to_output()
+
+    def create_normal_output(self) -> None:
+        if self.parser_module:
+            self.data_out = self.parser_module.parse(
+                self.data_in,
+                raw=self.raw,
+                quiet=self.quiet
+            )
+
+            if self.meta_out:
+                self.run_timestamp = datetime.now(timezone.utc)
+                self.add_metadata_to_output()
+
+
     def streaming_parse_and_print(self) -> None:
         """only supports UTF-8 string data for now"""
         self.data_in = sys.stdin
@@ -729,15 +768,11 @@ class JcCli():
         self.slicer()
 
         if self.parser_module:
-            self.data_out = self.parser_module.parse(
-                self.data_in,
-                raw=self.raw,
-                quiet=self.quiet
-            )
+            if self.slurp:
+                self.create_slurp_output()
 
-            if self.meta_out:
-                self.run_timestamp = datetime.now(timezone.utc)
-                self.add_metadata_to_output()
+            else:
+                self.create_normal_output()
 
             self.safe_print_out()
 
@@ -786,6 +821,7 @@ class JcCli():
         self.quiet = 'q' in self.options
         self.ignore_exceptions = self.options.count('q') > 1
         self.raw = 'r' in self.options
+        self.slurp = 's' in self.options
         self.meta_out = 'M' in self.options
         self.unbuffer = 'u' in self.options
         self.version_info = 'v' in self.options

jc/cli_data.py

@@ -11,6 +11,7 @@ long_options_map: Dict[str, List[str]] = {
     '--pretty': ['p', 'pretty print output'],
     '--quiet': ['q', 'suppress warnings (double to ignore streaming errors)'],
     '--raw': ['r', 'raw output'],
+    '--slurp': ['s', 'slurp multiple lines into an array'],
     '--unbuffer': ['u', 'unbuffer output'],
     '--version': ['v', 'version info'],
     '--yaml-out': ['y', 'YAML output'],

jc/lib.py

@@ -278,6 +278,18 @@ def _get_parser(parser_mod_name: str) -> ModuleType:
     modpath: str = 'jcparsers.' if parser_cli_name in local_parsers else 'jc.parsers.'
     return importlib.import_module(f'{modpath}{parser_mod_name}')
 
+def _parser_is_slurpable(parser: ModuleType) -> bool:
+    """
+    Returns True if this parser can use the `--slurp` command option, else False
+
+    parser is a parser module object.
+    """
+    tag_list = getattr(parser.info, 'tags', [])
+    if 'slurpable' in tag_list:
+        return True
+
+    return False
+
 def _parser_is_streaming(parser: ModuleType) -> bool:
     """
     Returns True if this is a streaming parser, else False
@@ -503,6 +515,30 @@ def streaming_parser_mod_list(
 
     return plist
 
+def slurpable_parser_mod_list(
+    show_hidden: bool = False,
+    show_deprecated: bool = False
+) -> List[str]:
+    """
+    Returns a list of slurpable parser module names. This function is a
+    subset of `parser_mod_list()`.
+    """
+    plist: List[str] = []
+    for p in parsers:
+        parser = _get_parser(p)
+
+        if _parser_is_slurpable(parser):
+
+            if not show_hidden and _parser_is_hidden(parser):
+                continue
+
+            if not show_deprecated and _parser_is_deprecated(parser):
+                continue
+
+            plist.append(_cliname_to_modname(p))
+
+    return plist
+
 def parser_info(
     parser_mod_name: Union[str, ModuleType],
     documentation: bool = False

jc/parsers/date.py

@@ -78,13 +78,13 @@ import jc.utils
 
 class info():
     """Provides parser metadata (version, author, etc.)"""
-    version = '2.5'
+    version = '2.6'
     description = '`date` command parser'
     author = 'Kelly Brazil'
     author_email = 'kellyjonbrazil@gmail.com'
     compatible = ['linux', 'darwin', 'freebsd']
     magic_commands = ['date']
-    tags = ['command']
+    tags = ['command', 'slurpable']
 
 
 __version__ = info.version

jc/parsers/datetime_iso.py

@@ -69,13 +69,13 @@ import jc.utils
 
 class info():
     """Provides parser metadata (version, author, etc.)"""
-    version = '1.0'
+    version = '1.1'
     description = 'ISO 8601 Datetime string parser'
     author = 'Kelly Brazil'
     author_email = 'kellyjonbrazil@gmail.com'
     details = 'Using the pyiso8601 library from https://github.com/micktwomey/pyiso8601/releases/tag/1.0.2'
     compatible = ['linux', 'aix', 'freebsd', 'darwin', 'win32', 'cygwin']
-    tags = ['standard', 'string']
+    tags = ['standard', 'string', 'slurpable']
 
 
 __version__ = info.version

jc/parsers/email_address.py

@@ -42,12 +42,12 @@ import jc.utils
 
 class info():
     """Provides parser metadata (version, author, etc.)"""
-    version = '1.0'
+    version = '1.1'
     description = 'Email Address string parser'
     author = 'Kelly Brazil'
     author_email = 'kellyjonbrazil@gmail.com'
     compatible = ['linux', 'darwin', 'cygwin', 'win32', 'aix', 'freebsd']
-    tags = ['standard', 'string']
+    tags = ['standard', 'string', 'slurpable']
 
 
 __version__ = info.version

jc/parsers/foo.py

@@ -49,10 +49,14 @@ class info():
     # compatible options: linux, darwin, cygwin, win32, aix, freebsd
     compatible = ['linux', 'darwin', 'cygwin', 'win32', 'aix', 'freebsd']
 
-    # tags options: generic, standard, file, string, binary, command
+    # tags options: generic, standard, file, string, binary, command, slurpable
     tags = ['command']
     magic_commands = ['foo']
 
+    # other attributes - only enable if needed
+    deprecated = False
+    hidden = False
+
 
 __version__ = info.version
 

jc/parsers/foo_s.py

@@ -55,14 +55,21 @@ class info():
     description = '`foo` command streaming parser'
     author = 'John Doe'
     author_email = 'johndoe@gmail.com'
+    # details = 'enter any other details here'
 
     # compatible options: linux, darwin, cygwin, win32, aix, freebsd
     compatible = ['linux', 'darwin', 'cygwin', 'win32', 'aix', 'freebsd']
 
-    # tags options: generic, standard, file, string, binary, command
+    # tags options: generic, standard, file, string, binary, command, slurpable
     tags = ['command']
+
+    # required for streaming parsers
     streaming = True
 
+    # other attributes - only enable if needed
+    deprecated = False
+    hidden = False
+
 
 __version__ = info.version
 

jc/parsers/ip_address.py

@@ -533,12 +533,12 @@ import jc.utils
 
 class info():
     """Provides parser metadata (version, author, etc.)"""
-    version = '1.3'
+    version = '1.4'
     description = 'IPv4 and IPv6 Address string parser'
     author = 'Kelly Brazil'
     author_email = 'kellyjonbrazil@gmail.com'
     compatible = ['linux', 'darwin', 'cygwin', 'win32', 'aix', 'freebsd']
-    tags = ['standard', 'string']
+    tags = ['standard', 'string', 'slurpable']
 
 
 __version__ = info.version

jc/parsers/jwt.py

@@ -51,12 +51,12 @@ import jc.utils
 
 class info():
     """Provides parser metadata (version, author, etc.)"""
-    version = '1.0'
+    version = '1.1'
     description = 'JWT string parser'
     author = 'Kelly Brazil'
     author_email = 'kellyjonbrazil@gmail.com'
     compatible = ['linux', 'darwin', 'cygwin', 'win32', 'aix', 'freebsd']
-    tags = ['standard', 'string']
+    tags = ['standard', 'string', 'slurpable']
 
 
 __version__ = info.version

jc/parsers/semver.py

@@ -54,12 +54,12 @@ import jc.utils
 
 class info():
     """Provides parser metadata (version, author, etc.)"""
-    version = '1.0'
+    version = '1.1'
     description = 'Semantic Version string parser'
     author = 'Kelly Brazil'
     author_email = 'kellyjonbrazil@gmail.com'
     compatible = ['linux', 'darwin', 'cygwin', 'win32', 'aix', 'freebsd']
-    tags = ['standard', 'string']
+    tags = ['standard', 'string', 'slurpable']
 
 
 __version__ = info.version

jc/parsers/timestamp.py

@@ -97,12 +97,12 @@ import jc.utils
 
 class info():
     """Provides parser metadata (version, author, etc.)"""
-    version = '1.0'
+    version = '1.1'
     description = 'Unix Epoch Timestamp string parser'
     author = 'Kelly Brazil'
     author_email = 'kellyjonbrazil@gmail.com'
     compatible = ['linux', 'aix', 'freebsd', 'darwin', 'win32', 'cygwin']
-    tags = ['standard', 'string']
+    tags = ['standard', 'string', 'slurpable']
 
 
 __version__ = info.version

jc/parsers/url.py

@@ -240,12 +240,12 @@ import jc.utils
 
 class info():
     """Provides parser metadata (version, author, etc.)"""
-    version = '1.1'
+    version = '1.2'
     description = 'URL string parser'
     author = 'Kelly Brazil'
     author_email = 'kellyjonbrazil@gmail.com'
     compatible = ['linux', 'darwin', 'cygwin', 'win32', 'aix', 'freebsd']
-    tags = ['standard', 'string']
+    tags = ['standard', 'string', 'slurpable']
 
 
 __version__ = info.version

jc/parsers/ver.py

@@ -89,13 +89,13 @@ import jc.utils
 
 class info():
     """Provides parser metadata (version, author, etc.)"""
-    version = '1.0'
+    version = '1.1'
     description = 'Version string parser'
     author = 'Kelly Brazil'
     author_email = 'kellyjonbrazil@gmail.com'
     details = 'Based on distutils/version.py from CPython 3.9.5.'
     compatible = ['linux', 'darwin', 'cygwin', 'win32', 'aix', 'freebsd']
-    tags = ['generic', 'string']
+    tags = ['generic', 'string', 'slurpable']
 
 
 __version__ = info.version