refine streaming parsers

docgen.sh

@@ -85,6 +85,9 @@ pydoc-markdown -m jc.lib "${toc_config}" > ../docs/lib.md
 echo Building docs for: utils
 pydoc-markdown -m jc.utils "${toc_config}" > ../docs/utils.md
 
+echo Building docs for: streaming
+pydoc-markdown -m jc.streaming "${toc_config}" > ../docs/streaming.md
+
 echo Building docs for: universal parser
 pydoc-markdown -m jc.parsers.universal "${toc_config}" > ../docs/parsers/universal.md
 

docs/parsers/rsync_s.md

@@ -122,4 +122,4 @@ Returns:
 ### Parser Information
 Compatibility:  linux, darwin, freebsd
 
-Version 1.1 by Kelly Brazil (kellyjonbrazil@gmail.com)
+Version 1.0 by Kelly Brazil (kellyjonbrazil@gmail.com)

docs/readme.md

@@ -14,6 +14,8 @@ and file-types to dictionaries and lists of dictionaries.
     >>> help('jc')
     >>> help('jc.lib')
     >>> help('jc.utils')
+    >>> help('jc.streaming')
+    >>> help('jc.parsers.universal')
     >>> jc.get_help('parser_module_name')
 
 ## Online Documentation

docs/streaming.md

@@ -0,0 +1,114 @@
+# Table of Contents
+
+* [jc.streaming](#jc.streaming)
+  * [streaming\_input\_type\_check](#jc.streaming.streaming_input_type_check)
+  * [streaming\_line\_input\_type\_check](#jc.streaming.streaming_line_input_type_check)
+  * [stream\_success](#jc.streaming.stream_success)
+  * [stream\_error](#jc.streaming.stream_error)
+  * [add\_jc\_meta](#jc.streaming.add_jc_meta)
+  * [raise\_or\_yield](#jc.streaming.raise_or_yield)
+
+<a id="jc.streaming"></a>
+
+# jc.streaming
+
+jc - JSON CLI output utility streaming utils
+
+<a id="jc.streaming.streaming_input_type_check"></a>
+
+### streaming\_input\_type\_check
+
+```python
+def streaming_input_type_check(data: Iterable) -> None
+```
+
+Ensure input data is an iterable, but not a string or bytes. Raises
+`TypeError` if not.
+
+<a id="jc.streaming.streaming_line_input_type_check"></a>
+
+### streaming\_line\_input\_type\_check
+
+```python
+def streaming_line_input_type_check(line: str) -> None
+```
+
+Ensure each line is a string. Raises `TypeError` if not.
+
+<a id="jc.streaming.stream_success"></a>
+
+### stream\_success
+
+```python
+def stream_success(output_line: Dict, ignore_exceptions: bool) -> Dict
+```
+
+Add `_jc_meta` object to output line if `ignore_exceptions=True`
+
+<a id="jc.streaming.stream_error"></a>
+
+### stream\_error
+
+```python
+def stream_error(e: BaseException, line: str) -> Dict
+```
+
+Return an error `_jc_meta` field.
+
+<a id="jc.streaming.add_jc_meta"></a>
+
+### add\_jc\_meta
+
+```python
+def add_jc_meta(func)
+```
+
+Decorator for streaming parsers to add stream_success and stream_error
+objects. This simplifies the yield lines in the streaming parsers.
+
+With the decorator on parse():
+
+    # successfully parsed line:
+    yield output_line if raw else _process(output_line)
+
+    # unsuccessfully parsed line:
+    except Exception as e:
+        yield raise_or_yield(ignore_exceptions, e, line)
+
+Without the decorator on parse():
+
+    # successfully parsed line:
+    if raw:
+        yield stream_success(output_line, ignore_exceptions)
+    else:
+        stream_success(_process(output_line), ignore_exceptions)
+
+    # unsuccessfully parsed line:
+    except Exception as e:
+        yield stream_error(raise_or_yield(ignore_exceptions, e, line))
+
+In all cases above:
+
+    output_line:  (Dict)  successfully parsed line yielded as a dict
+
+    e:            (BaseException)  exception object as the first value
+                  of the tuple if the line was not successfully parsed.
+
+    line:         (str)  string of the original line that did not
+                  successfully parse.
+
+    ignore_exceptions:  (bool)  continue processing lines and ignore
+                        exceptions if True.
+
+<a id="jc.streaming.raise_or_yield"></a>
+
+### raise\_or\_yield
+
+```python
+def raise_or_yield(ignore_exceptions: bool, e: BaseException, line: str) -> tuple
+```
+
+Return the exception object and line string if ignore_exceptions is
+True. Otherwise, re-raise the exception from the exception object with
+an annotation.
+

docs/utils.md

@@ -8,12 +8,7 @@
   * [convert\_to\_int](#jc.utils.convert_to_int)
   * [convert\_to\_float](#jc.utils.convert_to_float)
   * [convert\_to\_bool](#jc.utils.convert_to_bool)
-  * [stream\_success](#jc.utils.stream_success)
-  * [stream\_error](#jc.utils.stream_error)
-  * [add\_jc\_meta](#jc.utils.add_jc_meta)
   * [input\_type\_check](#jc.utils.input_type_check)
-  * [streaming\_input\_type\_check](#jc.utils.streaming_input_type_check)
-  * [streaming\_line\_input\_type\_check](#jc.utils.streaming_line_input_type_check)
   * [timestamp](#jc.utils.timestamp)
     * [\_\_init\_\_](#jc.utils.timestamp.__init__)
 
@@ -166,73 +161,6 @@ Returns:
     True/False      False unless a 'truthy' number or string is found
                     ('y', 'yes', 'true', '1', 1, -1, etc.)
 
-<a id="jc.utils.stream_success"></a>
-
-### stream\_success
-
-```python
-def stream_success(output_line: Dict, ignore_exceptions: bool) -> Dict
-```
-
-Add `_jc_meta` object to output line if `ignore_exceptions=True`
-
-<a id="jc.utils.stream_error"></a>
-
-### stream\_error
-
-```python
-def stream_error(e: BaseException, line: str) -> Dict
-```
-
-Return an error `_jc_meta` field.
-
-<a id="jc.utils.add_jc_meta"></a>
-
-### add\_jc\_meta
-
-```python
-def add_jc_meta(func)
-```
-
-Decorator for streaming parsers to add stream_success and stream_error
-objects. This simplifies the yield lines in the streaming parsers.
-
-With the decorator on parse():
-
-    # successfully parsed line:
-    yield output_line if raw else _process(output_line)
-
-    # unsuccessfully parsed line:
-    except Exception as e:
-        if not ignore_exceptions:
-            e.args = (str(e) + ignore_exceptions_msg,)
-            raise e
-
-        yield e, line
-
-Without the decorator on parse():
-
-    # successfully parsed line:
-    yield stream_success(output_line, ignore_exceptions) if raw else stream_success(_process(output_line), ignore_exceptions)
-
-    # unsuccessfully parsed line:
-    except Exception as e:
-        if not ignore_exceptions:
-            e.args = (str(e) + ignore_exceptions_msg,)
-            raise e
-
-        yield stream_error(e, line)
-
-In all cases above:
-
-    output_line:  (Dict):  successfully parsed line yielded as a dict
-
-    e:            (BaseException):  exception object as the first value
-                  of the tuple if the line was not successfully parsed.
-
-    line:         (str):  string of the original line that did not
-                  successfully parse.
-
 <a id="jc.utils.input_type_check"></a>
 
 ### input\_type\_check
@@ -243,27 +171,6 @@ def input_type_check(data: str) -> None
 
 Ensure input data is a string. Raises `TypeError` if not.
 
-<a id="jc.utils.streaming_input_type_check"></a>
-
-### streaming\_input\_type\_check
-
-```python
-def streaming_input_type_check(data: Iterable) -> None
-```
-
-Ensure input data is an iterable, but not a string or bytes. Raises
-`TypeError` if not.
-
-<a id="jc.utils.streaming_line_input_type_check"></a>
-
-### streaming\_line\_input\_type\_check
-
-```python
-def streaming_line_input_type_check(line: str) -> None
-```
-
-Ensure each line is a string. Raises `TypeError` if not.
-
 <a id="jc.utils.timestamp"></a>
 
 ### timestamp Objects

jc/__init__.py

@@ -10,6 +10,8 @@ and file-types to dictionaries and lists of dictionaries.
     >>> help('jc')
     >>> help('jc.lib')
     >>> help('jc.utils')
+    >>> help('jc.streaming')
+    >>> help('jc.parsers.universal')
     >>> jc.get_help('parser_module_name')
 
 ## Online Documentation

jc/parsers/csv_s.py

@@ -66,7 +66,7 @@ Examples:
 import itertools
 import csv
 import jc.utils
-from jc.utils import ignore_exceptions_msg, add_jc_meta
+from jc.streaming import streaming_input_type_check, add_jc_meta, raise_or_yield
 from jc.exceptions import ParseError
 
 
@@ -124,7 +124,7 @@ def parse(data, raw=False, quiet=False, ignore_exceptions=False):
         Iterator object
     """
     jc.utils.compatibility(__name__, info.compatible, quiet)
-    jc.utils.streaming_input_type_check(data)
+    streaming_input_type_check(data)
 
     # convert data to an iterable in case a sequence like a list is used as input.
     # this allows the exhaustion of the input so we don't double-process later.
@@ -158,8 +158,4 @@ def parse(data, raw=False, quiet=False, ignore_exceptions=False):
         try:
             yield row if raw else _process(row)
         except Exception as e:
-            if not ignore_exceptions:
-                e.args = (str(e) + ignore_exceptions_msg,)
-                raise e
-
-            yield e, str(row)
+            yield raise_or_yield(ignore_exceptions, e, str(row))

jc/parsers/foo_s.py

@@ -51,7 +51,9 @@ Examples:
 """
 from typing import Dict, Iterable, Union
 import jc.utils
-from jc.utils import ignore_exceptions_msg, add_jc_meta
+from jc.streaming import (
+    add_jc_meta, streaming_input_type_check, streaming_line_input_type_check, raise_or_yield
+)
 from jc.exceptions import ParseError
 
 
@@ -119,12 +121,12 @@ def parse(
         Iterator object
     """
     jc.utils.compatibility(__name__, info.compatible, quiet)
-    jc.utils.streaming_input_type_check(data)
+    streaming_input_type_check(data)
 
     for line in data:
         try:
+            streaming_line_input_type_check(line)
             output_line: Dict = {}
-            jc.utils.streaming_line_input_type_check(line)
 
             # parse the content here
             # check out helper functions in jc.utils
@@ -136,8 +138,4 @@ def parse(
                 raise ParseError('Not foo data')
 
         except Exception as e:
-            if not ignore_exceptions:
-                e.args = (str(e) + ignore_exceptions_msg,)
-                raise e
-
-            yield e, line
+            yield raise_or_yield(ignore_exceptions, e, line)

jc/parsers/iostat_s.py

@@ -101,7 +101,9 @@ Examples:
     ...
 """
 import jc.utils
-from jc.utils import ignore_exceptions_msg, add_jc_meta
+from jc.streaming import (
+    add_jc_meta, streaming_input_type_check, streaming_line_input_type_check, raise_or_yield
+)
 from jc.exceptions import ParseError
 import jc.parsers.universal
 
@@ -183,7 +185,7 @@ def parse(data, raw=False, quiet=False, ignore_exceptions=False):
         Iterator object
     """
     jc.utils.compatibility(__name__, info.compatible, quiet)
-    jc.utils.streaming_input_type_check(data)
+    streaming_input_type_check(data)
 
     section = ''  # either 'cpu' or 'device'
     headers = ''
@@ -192,10 +194,9 @@ def parse(data, raw=False, quiet=False, ignore_exceptions=False):
 
     for line in data:
         try:
-            jc.utils.streaming_line_input_type_check(line)
+            streaming_line_input_type_check(line)
             output_line = {}
 
-
             # ignore blank lines and header line
             if line == '\n' or line == '' or line.startswith('Linux'):
                 continue
@@ -231,8 +232,4 @@ def parse(data, raw=False, quiet=False, ignore_exceptions=False):
                 raise ParseError('Not iostat data')
 
         except Exception as e:
-            if not ignore_exceptions:
-                e.args = (str(e) + ignore_exceptions_msg,)
-                raise e
-
-            yield e, line
+            yield raise_or_yield(ignore_exceptions, e, line)

jc/parsers/ls_s.py

@@ -79,7 +79,9 @@ Examples:
 """
 import re
 import jc.utils
-from jc.utils import ignore_exceptions_msg, add_jc_meta
+from jc.streaming import (
+    add_jc_meta, streaming_input_type_check, streaming_line_input_type_check, raise_or_yield
+)
 from jc.exceptions import ParseError
 
 
@@ -146,13 +148,13 @@ def parse(data, raw=False, quiet=False, ignore_exceptions=False):
         Iterator object
     """
     jc.utils.compatibility(__name__, info.compatible, quiet)
-    jc.utils.streaming_input_type_check(data)
+    streaming_input_type_check(data)
 
     parent = ''
 
     for line in data:
         try:
-            jc.utils.streaming_line_input_type_check(line)
+            streaming_line_input_type_check(line)
 
             # skip line if it starts with 'total 1234'
             if re.match(r'total [0-9]+', line):
@@ -200,8 +202,4 @@ def parse(data, raw=False, quiet=False, ignore_exceptions=False):
             yield output_line if raw else _process(output_line)
 
         except Exception as e:
-            if not ignore_exceptions:
-                e.args = (str(e) + ignore_exceptions_msg,)
-                raise e
-
-            yield e, line
+            yield raise_or_yield(ignore_exceptions, e, line)

jc/parsers/ping_s.py

@@ -86,10 +86,10 @@ Examples:
 import string
 import ipaddress
 import jc.utils
-from jc.exceptions import ParseError
 from jc.streaming import (
     add_jc_meta, streaming_input_type_check, streaming_line_input_type_check, raise_or_yield
 )
+from jc.exceptions import ParseError
 
 
 class info():
@@ -500,8 +500,8 @@ def parse(data, raw=False, quiet=False, ignore_exceptions=False):
 
     for line in data:
         try:
-            output_line = {}
             streaming_line_input_type_check(line)
+            output_line = {}
 
             # skip blank lines
             if line.strip() == '':

jc/parsers/rsync_s.py

@@ -89,13 +89,13 @@ Examples:
 import re
 from typing import Dict, Iterable, Union
 import jc.utils
-from jc.utils import ignore_exceptions_msg, add_jc_meta
-from jc.exceptions import ParseError
-
+from jc.streaming import (
+    add_jc_meta, streaming_input_type_check, streaming_line_input_type_check, raise_or_yield
+)
 
 class info():
     """Provides parser metadata (version, author, etc.)"""
-    version = '1.1'
+    version = '1.0'
     description = '`rsync` command streaming parser'
     author = 'Kelly Brazil'
     author_email = 'kellyjonbrazil@gmail.com'
@@ -168,7 +168,7 @@ def parse(
         Iterator object
     """
     jc.utils.compatibility(__name__, info.compatible, quiet)
-    jc.utils.streaming_input_type_check(data)
+    streaming_input_type_check(data)
 
     summary: Dict = {}
     process: str = ''
@@ -272,7 +272,7 @@ def parse(
 
     for line in data:
         try:
-            jc.utils.streaming_line_input_type_check(line)
+            streaming_line_input_type_check(line)
             output_line: Dict = {}
 
             # ignore blank lines
@@ -452,19 +452,12 @@ def parse(
                 continue
 
         except Exception as e:
-            if not ignore_exceptions:
-                e.args = (str(e) + ignore_exceptions_msg,)
-                raise e
-
-            yield e, line
+            yield raise_or_yield(ignore_exceptions, e, line)
 
+    # gather final item
     try:
         if summary:
             yield summary if raw else _process(summary)
 
     except Exception as e:
-            if not ignore_exceptions:
-                e.args = (str(e) + ignore_exceptions_msg,)
-                raise e
-
-            yield e, line
+        yield raise_or_yield(ignore_exceptions, e, '')

jc/parsers/stat_s.py

@@ -83,7 +83,9 @@ Examples:
 """
 import shlex
 import jc.utils
-from jc.utils import ignore_exceptions_msg, add_jc_meta
+from jc.streaming import (
+    add_jc_meta, streaming_input_type_check, streaming_line_input_type_check, raise_or_yield
+)
 from jc.exceptions import ParseError
 
 
@@ -154,14 +156,14 @@ def parse(data, raw=False, quiet=False, ignore_exceptions=False):
         Iterator object
     """
     jc.utils.compatibility(__name__, info.compatible, quiet)
-    jc.utils.streaming_input_type_check(data)
+    streaming_input_type_check(data)
 
     output_line = {}
     os_type = ''
 
     for line in data:
         try:
-            jc.utils.streaming_line_input_type_check(line)
+            streaming_line_input_type_check(line)
             line = line.rstrip()
 
             # ignore blank lines
@@ -287,20 +289,12 @@ def parse(data, raw=False, quiet=False, ignore_exceptions=False):
                     output_line = {}
 
         except Exception as e:
-            if not ignore_exceptions:
-                e.args = (str(e) + ignore_exceptions_msg,)
-                raise e
+            yield raise_or_yield(ignore_exceptions, e, line)
 
-            yield e, line
-
-    try:
     # gather final item
+    try:
         if output_line:
             yield output_line if raw else _process(output_line)
 
     except Exception as e:
-            if not ignore_exceptions:
-                e.args = (str(e) + ignore_exceptions_msg,)
-                raise e
-
-            yield e, line
+        yield raise_or_yield(ignore_exceptions, e, '')

jc/parsers/vmstat_s.py

@@ -101,7 +101,9 @@ Examples:
     ...
 """
 import jc.utils
-from jc.utils import ignore_exceptions_msg, add_jc_meta
+from jc.streaming import (
+    add_jc_meta, streaming_input_type_check, streaming_line_input_type_check, raise_or_yield
+)
 from jc.exceptions import ParseError
 
 
@@ -173,7 +175,7 @@ def parse(data, raw=False, quiet=False, ignore_exceptions=False):
         Iterator object
     """
     jc.utils.compatibility(__name__, info.compatible, quiet)
-    jc.utils.streaming_input_type_check(data)
+    streaming_input_type_check(data)
 
     procs = None
     buff_cache = None
@@ -182,9 +184,9 @@ def parse(data, raw=False, quiet=False, ignore_exceptions=False):
     tz = None
 
     for line in data:
-        output_line = {}
         try:
-            jc.utils.streaming_line_input_type_check(line)
+            streaming_line_input_type_check(line)
+            output_line = {}
 
             # skip blank lines
             if line.strip() == '':
@@ -272,8 +274,4 @@ def parse(data, raw=False, quiet=False, ignore_exceptions=False):
                 raise ParseError('Not vmstat data')
 
         except Exception as e:
-            if not ignore_exceptions:
-                e.args = (str(e) + ignore_exceptions_msg,)
-                raise e
-
-            yield e, line
+            yield raise_or_yield(ignore_exceptions, e, line)

jc/streaming.py

@@ -4,6 +4,21 @@ from functools import wraps
 from typing import Dict, Iterable
 
 
+def streaming_input_type_check(data: Iterable) -> None:
+    """
+    Ensure input data is an iterable, but not a string or bytes. Raises
+    `TypeError` if not.
+    """
+    if not hasattr(data, '__iter__') or isinstance(data, (str, bytes)):
+        raise TypeError("Input data must be a non-string iterable object.")
+
+
+def streaming_line_input_type_check(line: str) -> None:
+    """Ensure each line is a string. Raises `TypeError` if not."""
+    if not isinstance(line, str):
+        raise TypeError("Input line must be a 'str' object.")
+
+
 def stream_success(output_line: Dict, ignore_exceptions: bool) -> Dict:
     """Add `_jc_meta` object to output line if `ignore_exceptions=True`"""
     if ignore_exceptions:
@@ -43,8 +58,10 @@ def add_jc_meta(func):
     Without the decorator on parse():
 
         # successfully parsed line:
-        yield stream_success(output_line, ignore_exceptions) if raw \\
-            else stream_success(_process(output_line), ignore_exceptions)
+        if raw:
+            yield stream_success(output_line, ignore_exceptions)
+        else:
+            stream_success(_process(output_line), ignore_exceptions)
 
         # unsuccessfully parsed line:
         except Exception as e:
@@ -82,26 +99,16 @@ def add_jc_meta(func):
     return wrapper
 
 
-def streaming_input_type_check(data: Iterable) -> None:
-    """
-    Ensure input data is an iterable, but not a string or bytes. Raises
-    `TypeError` if not.
-    """
-    if not hasattr(data, '__iter__') or isinstance(data, (str, bytes)):
-        raise TypeError("Input data must be a non-string iterable object.")
-
-
-def streaming_line_input_type_check(line: str) -> None:
-    """Ensure each line is a string. Raises `TypeError` if not."""
-    if not isinstance(line, str):
-        raise TypeError("Input line must be a 'str' object.")
-
-
 def raise_or_yield(
     ignore_exceptions: bool,
     e: BaseException,
     line: str
 ) -> tuple:
+    """
+    Return the exception object and line string if ignore_exceptions is
+    True. Otherwise, re-raise the exception from the exception object with
+    an annotation.
+    """
     ignore_exceptions_msg = '... Use the ignore_exceptions option (-qq) to ignore streaming parser errors.'
 
     if not ignore_exceptions:

man/jc.1

@@ -1,4 +1,4 @@
-.TH jc 1 2022-02-04 1.18.3 "JSON CLI output utility"
+.TH jc 1 2022-02-07 1.18.3 "JSON CLI output utility"
 .SH NAME
 jc \- JSONifies the output of many CLI tools and file-types
 .SH SYNOPSIS