Improved integer suffix

Signed-off-by: Andrea Zoppi <[email protected]>

docs/_autosummary/hexrec.hexdump.CHAR_PRINTABLE.rst

@@ -0,0 +1,6 @@
+CHAR\_PRINTABLE
+===============
+
+.. currentmodule:: hexrec.hexdump
+
+.. autodata:: CHAR_PRINTABLE

docs/_autosummary/hexrec.hexdump.CHAR_TOKENS.rst

@@ -0,0 +1,6 @@
+CHAR\_TOKENS
+============
+
+.. currentmodule:: hexrec.hexdump
+
+.. autodata:: CHAR_TOKENS

docs/_autosummary/hexrec.hexdump.DEFAULT_FORMAT_ORDER.rst

@@ -0,0 +1,6 @@
+DEFAULT\_FORMAT\_ORDER
+======================
+
+.. currentmodule:: hexrec.hexdump
+
+.. autodata:: DEFAULT_FORMAT_ORDER

docs/_autosummary/hexrec.hexdump.hexdump.rst

@@ -0,0 +1,6 @@
+hexdump
+=======
+
+.. currentmodule:: hexrec.hexdump
+
+.. autofunction:: hexdump

docs/_autosummary/hexrec.hexdump.rst

@@ -0,0 +1,49 @@
+hexdump
+=======
+
+.. automodule:: hexrec.hexdump
+
+
+
+
+    .. rubric:: Attributes
+
+    .. autosummary::
+        :toctree:
+        :template: custom-base-template.rst
+        :nosignatures:
+
+        ~CHAR_PRINTABLE
+        ~CHAR_TOKENS
+        ~DEFAULT_FORMAT_ORDER
+
+
+
+
+
+
+    .. rubric:: Functions
+
+    .. autosummary::
+        :toctree:
+        :template: custom-base-template.rst
+        :nosignatures:
+
+        ~hexdump
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+

docs/_autosummary/hexrec.utils.SUFFIX_SCALE.rst

@@ -0,0 +1,6 @@
+SUFFIX\_SCALE
+=============
+
+.. currentmodule:: hexrec.utils
+
+.. autodata:: SUFFIX_SCALE

docs/_autosummary/hexrec.utils.rst

@@ -13,6 +13,7 @@
         :template: custom-base-template.rst
         :nosignatures:
 
+        ~SUFFIX_SCALE
         ~DEFAULT_DELETE
 
 

docs/reference.rst

@@ -15,5 +15,6 @@ Reference
     hexrec.formats.srec
     hexrec.formats.titxt
     hexrec.formats.xtek
+    hexrec.hexdump
     hexrec.utils
     hexrec.xxd

src/hexrec/cli.py

@@ -660,10 +660,10 @@ def flood(
 """)
 @click.option('-n', '--length', 'length', type=BASED_INT, help="""
     Interpret only length bytes of input.
-""")  # FIXME: SUFFIXED_INT for hexdump compatible integers
+""")
 @click.option('-s', '--skip', 'skip', type=BASED_INT, help="""
     Skip offset bytes from the beginning of the input.
-""")  # FIXME: SUFFIXED_INT for hexdump compatible integers
+""")
 @click.option('-v', '--no_squeezing', 'no_squeezing', is_flag=True, help="""
     The -v option causes hexdump to display all input data.
     Without the -v option, any number of groups of output lines
@@ -678,8 +678,8 @@ def flood(
     Forces the input file format.
     Required for the standard input.
 """)
-@click.option('-V', '--version', is_flag=True, is_eager=True, expose_value=False,
-              callback=print_hexdump_version, help="""
+@click.option('-V', '--version', is_flag=True, is_eager=True,
+              expose_value=False, callback=print_hexdump_version, help="""
     Print version and exit.
 """)
 @click.argument('infile', type=FILE_PATH_IN)
@@ -698,7 +698,6 @@ def hexdump(
     upper: bool,
     input_format: Optional[str],  # TODO:
 ) -> None:
-    # TODO: __doc__
     r"""Display file contents in hexadecimal, decimal, octal, or ascii.
 
     The hexdump utility is a filter which displays the specified
@@ -788,10 +787,10 @@ def hexdump(
 """)
 @click.option('-n', '--length', 'length', type=BASED_INT, help="""
     Interpret only length bytes of input.
-""")  # FIXME: SUFFIXED_INT for hexdump compatible integers
+""")
 @click.option('-s', '--skip', 'skip', type=BASED_INT, help="""
     Skip offset bytes from the beginning of the input.
-""")  # FIXME: SUFFIXED_INT for hexdump compatible integers
+""")
 @click.option('-v', '--no_squeezing', 'no_squeezing', is_flag=True, help="""
     The -v option causes hexdump to display all input data.
     Without the -v option, any number of groups of output lines
@@ -806,8 +805,8 @@ def hexdump(
     Forces the input file format.
     Required for the standard input.
 """)
-@click.option('-V', '--version', is_flag=True, is_eager=True, expose_value=False,
-              callback=print_hexdump_version, help="""
+@click.option('-V', '--version', is_flag=True, is_eager=True,
+              expose_value=False, callback=print_hexdump_version, help="""
     Print version and exit.
 """)
 @click.argument('infile', type=FILE_PATH_IN)
@@ -825,7 +824,6 @@ def hd(
     upper: bool,
     input_format: Optional[str],  # TODO:
 ) -> None:
-    # TODO: __doc__
     r"""Display file contents in hexadecimal, decimal, octal, or ascii.
 
     The hexdump utility is a filter which displays the specified
@@ -1199,8 +1197,8 @@ def del_header(
 @click.option('-u', '--upper', 'upper', is_flag=True, help="""
     Uses upper case hex letters on data only.
 """)
-@click.option('-v', '--version', is_flag=True, is_eager=True, expose_value=False,
-              callback=print_version, help="""
+@click.option('-v', '--version', is_flag=True, is_eager=True,
+              expose_value=False, callback=print_version, help="""
     Prints the package version number.
 """)
 @click.argument('infile', type=FILE_PATH_IN)

src/hexrec/hexdump.py

@@ -523,13 +523,14 @@ def hexdump(
         offset = 0
         last_chunk = None
         squeezing = False
+        read = instream.read
         write = outstream.write
 
         while True:
             if length is None:
-                chunk = instream.read(width)
+                chunk = read(width)
             else:
-                chunk = instream.read(min(width, length - offset))
+                chunk = read(min(width, length - offset))
 
             if not chunk:
                 break

src/hexrec/utils.py

@@ -44,11 +44,45 @@
 BIN8_TO_BYTES: List[bytes] = [bin(i)[2:].zfill(8).encode() for i in range(256)]
 BYTES_TO_BIN8: Mapping[bytes, int] = {s: i for i, s in enumerate(BIN8_TO_BYTES)}
 
+SUFFIX_SCALE: Mapping[str, int] = {
+    'k': 2**10,
+    'm': 2**20,
+    'g': 2**30,
+    't': 2**40,
+    'p': 2**50,
+    'e': 2**60,
+    'z': 2**70,
+    'y': 2**80,
+
+    'kib': 2**10,
+    'mib': 2**20,
+    'gib': 2**30,
+    'tib': 2**40,
+    'pib': 2**50,
+    'eib': 2**60,
+    'zib': 2**70,
+    'yib': 2**80,
+
+    'kb': 10**3,
+    'mb': 10**6,
+    'gb': 10**9,
+    'tb': 10**12,
+    'pb': 10**15,
+    'eb': 10**18,
+    'zb': 10**21,
+    'yb': 10**24,
+}
+r"""Integer suffix to scale factor."""
+
 INT_REGEX = re.compile(r'^\s*(?P<sign>[+-]?)\s*'
                        r'(?P<prefix>(0x|0b|0o|0)?)'
                        r'(?P<value>[a-f0-9]+)'
                        r'(?P<suffix>h?)'
-                       r'(?P<scale>[km]?)\s*$')
+                       r'\s*(?P<scale>('
+                       r'k|m|g|t|p|e|z|y|'
+                       r'kib|mib|gib|tib|pib|eib|zib|yib|'
+                       r'kb|mb|gb|tb|pb|eb|zb|yb'
+                       r')?)\s*$')
 
 DEFAULT_DELETE: bytes = b' \t.-:\r\n'
 r"""Delete from hex strings.
@@ -167,8 +201,8 @@ def parse_int(
             either prefixed with ``0x`` or postfixed with ``h`` to convert
             from a hexadecimal representation, or prefixed with ``0b`` from
             binary; a prefix of only ``0`` converts from octal.
-            A further suffix of ``k`` or ``m`` scales as *kibibyte* or
-            *mebibyte*.
+            A further suffix applies a scale factor as per
+            :data:`SUFFIX_SCALE`.
             A ``None`` value evaluates as ``None``.
             Any other object class will call the standard :func:`int`.
 
@@ -214,10 +248,7 @@ def parse_int(
         else:
             i = int(value, 10)
 
-        if scale == 'k':
-            i <<= 10
-        elif scale == 'm':
-            i <<= 20
+        i *= SUFFIX_SCALE.get((scale or '').lower(), 1)
 
         if sign == '-':
             i = -i

tests/test_utils.py

@@ -31,8 +31,17 @@
     '0o1234567': 0o1234567,
     '0O1234567': 0o1234567,
 
-    '1k': 1 << 10,
-    '1m': 1 << 20,
+    '1k': 2**10,
+    '1M': 2**20,
+    '1 G': 2**30,
+
+    '1KiB': 2**10,
+    '1 mib': 2**20,
+    '1GiB': 2**30,
+
+    '1 KB': 10**3,
+    '1MB': 10**6,
+    '1gb': 10**9,
 
     b'456': 456,
     123: 123,