basic hexdumper

TODO.norg

@@ -3,7 +3,12 @@ This is a list of tasks that would be cool to add.
 * Tasks
 ** Basic
 *** Files
-		- ( ) Hex dumper
+		- (-) Hex dumper
+			- (x) Dump basic files with format
+			- (x) Dump basic files with chars
+			- (x) Be able to dump larger files or put out an error
+			- ( ) Stop reading when read gets blocked /somehow/
+			- ( ) Install script to system
 *** Networking
 		- ( ) Mini curl
 *** Packaging

Tasks.md

@@ -406,37 +406,84 @@ don't like windows either, so no support for installing stuff on windows.
 ### A. Hexdumper
 Difficulty: 3/5
 
-
 1. Dump the data of [data/metasyntactic.md](./data/metasyntactic.md) -- In
    Hexadecimal.
 2. Make the dumped Bytes look pretty, something like the example below:
+3. Make use of command line arguments to add a help option (triggered with `-h` or
+   `--help`) and a `-C` or `--chars` option that adds another section that
+   prints the bytes interpreted as text. Those bytes that have no text
+   representation should be displayed as `.`. You may use the `argparse` library
+   to work with the arguments.
 
 <details>
     <summary>Hexdump Example Display</summary>
 
-`data/metasyntactic.md` looks like this when hexdumped:
+`data/metasyntactic.md` should look like this when hexdumped:
 
 ```text
 Line      Data
 =================================================
-0000000 ┃ 6f4e 6574 203a 6854 7369 6920 2073 6874
+0000000 | 6f4e 6574 203a 6854 7369 6920 2073 6874
-0000010 ┃ 2065 6957 696b 6570 6964 2061 6170 6567
+0000010 | 2065 6957 696b 6570 6964 2061 6170 6567
-0000020 ┃ 6620 726f 6d20 7465 7361 6e79 6174 7463
+0000020 | 6620 726f 6d20 7465 7361 6e79 6174 7463
-0000030 ┃ 6369 7620 7261 6169 6c62 7365 6920 206e
+0000030 | 6369 7620 7261 6169 6c62 7365 6920 206e
-0000040 ┃ 6e45 6c67 7369 2c68 3220 3230 2d33 3930
+0000040 | 6e45 6c67 7369 2c68 3220 3230 2d33 3930
-0000050 ┃ 302d 2e35 4620 6e69 2064 6874 0a65 7075
+0000050 | 302d 2e35 4620 6e69 2064 6874 0a65 7075
-0000060 ┃ 7420 206f 6164 6574 6f20 6972 6967 616e
+0000060 | 7420 206f 6164 6574 6f20 6972 6967 616e
-0000070 ┃ 206c 685b 7265 5d65 6828 7474 7370 2f3a
+0000070 | 206c 685b 7265 5d65 6828 7474 7370 2f3a
-0000080 ┃ 652f 2e6e 6977 696b 6570 6964 2e61 726f
+0000080 | 652f 2e6e 6977 696b 6570 6964 2e61 726f
-0000090 ┃ 2f67 6977 696b 4d2f 7465 7361 6e79 6174
+0000090 | 2f67 6977 696b 4d2f 7465 7361 6e79 6174
-00000a0 ┃ 7463 6369 765f 7261 6169 6c62 2965 0a2e
+00000a0 | 7463 6369 765f 7261 6169 6c62 2965 0a2e
-00000b0 ┃ 230a 4d20 7465 7361 6e79 6174 7463 6369
+00000b0 | 230a 4d20 7465 7361 6e79 6174 7463 6369
-00000c0 ┃ 7620 7261 6169 6c62 0a65 230a 2023 6f54
+00000c0 | 7620 7261 6169 6c62 0a65 230a 2023 6f54
-00000d0 ┃ 6c6f 0a73 460a 6f72 206d 6957 696b 6570
+00000d0 | 6c6f 0a73 460a 6f72 206d 6957 696b 6570
-00000e0 ┃ 6964 2c61 7420 6568 6620 6572 2065 6e65
+00000e0 | 6964 2c61 7420 6568 6620 6572 2065 6e65
-00000f0 ┃ 7963 6c63 706f 6465 6169 540a 6968 2073
+00000f0 | 7963 6c63 706f 6465 6169 540a 6968 2073
-0000100 ┃ 7261 6974 6c63 2065 7369 6120 6f62 7475
+0000100 | 7261 6974 6c63 2065 7369 6120 6f62 7475
-0000110 ┃ 6d20 7465 7361 6e79 6174 7463 6369 7620
+0000110 | 6d20 7465 7361 6e79 6174 7463 6369 7620
+...
+```
+
+And like this when hexdumped with `-C`:
+
+```text
+Line      Data                                     Text
+======================================================================
+0000000 | 6f4e 6574 203a 6854 7369 6920 2073 6874 |Note: This is th|
+0000010 | 2065 6957 696b 6570 6964 2061 6170 6567 |e Wikipedia page|
+0000020 | 6620 726f 6d20 7465 7361 6e79 6174 7463 | for metasyntact|
+0000030 | 6369 7620 7261 6169 6c62 7365 6920 206e |ic variables in |
+0000040 | 6e45 6c67 7369 2c68 3220 3230 2d33 3930 |English, 2023-09|
+0000050 | 302d 2e35 4620 6e69 2064 6874 0a65 7075 |-05. Find the.up|
+0000060 | 7420 206f 6164 6574 6f20 6972 6967 616e | to date origina|
+0000070 | 206c 685b 7265 5d65 6828 7474 7370 2f3a |l [here](https:/|
+0000080 | 652f 2e6e 6977 696b 6570 6964 2e61 726f |/en.wikipedia.or|
+0000090 | 2f67 6977 696b 4d2f 7465 7361 6e79 6174 |g/wiki/Metasynta|
+00000a0 | 7463 6369 765f 7261 6169 6c62 2965 0a2e |ctic_variable)..|
+00000b0 | 230a 4d20 7465 7361 6e79 6174 7463 6369 |.# Metasyntactic|
+00000c0 | 7620 7261 6169 6c62 0a65 230a 2023 6f54 | variable..## To|
+00000d0 | 6c6f 0a73 460a 6f72 206d 6957 696b 6570 |ols..From Wikipe|
+00000e0 | 6964 2c61 7420 6568 6620 6572 2065 6e65 |dia, the free en|
+00000f0 | 7963 6c63 706f 6465 6169 540a 6968 2073 |cyclopedia.This |
 ...
 ```
 </details>
+
+<details>
+<summary>Hints</summary>
+
+
+
+</details>
+
+<details>
+<summary>Solution</summary>
+
+[Code Example](./src/hexdumper.py)
+
+</details>
+
+### B. Packaging your hexdumper
+
+1. Install `pip`, on debian based systems you can do that with `apt-get install
+   python3-pip`.

src/hexdumper.py

@@ -0,0 +1,104 @@
+#!/usr/bin/env python3
+import argparse
+import os
+import sys
+
+# 2**30 bytes aka 1 Mebibyte
+MAX_SIZE: int = 0x100000
+
+
+
+def humanbytes(B):
+    """Return the given bytes as a human friendly KB, MB, GB, or TB string."""
+    B = float(B)
+    KB = float(1024)
+    MB = float(KB ** 2) # 1,048,576
+    GB = float(KB ** 3) # 1,073,741,824
+    TB = float(KB ** 4) # 1,099,511,627,776
+
+    if B < KB:
+        return '{0} {1}'.format(B,'Bytes' if 0 == B > 1 else 'Byte')
+    elif KB <= B < MB:
+        return '{0:.2f} KB'.format(B / KB)
+    elif MB <= B < GB:
+        return '{0:.2f} MB'.format(B / MB)
+    elif GB <= B < TB:
+        return '{0:.2f} GB'.format(B / GB)
+    elif TB <= B:
+        return '{0:.2f} TB'.format(B / TB)
+
+def main():
+    """Dump a file"""
+    # arg parsing
+    parser = argparse.ArgumentParser(
+        prog="hexer",
+        description="Dumps data as hex"
+    )
+    parser.add_argument("file")
+    parser.add_argument("-c", "--chars", action="store_true")
+    args = parser.parse_args()
+
+    # open file
+    try:
+        file = open(args.file, "rb")
+    except Exception as e:
+        print(f"Could not open file '{args.file}': {e}")
+        sys.exit(1)
+
+    # check if the file has a reasonable size to dump
+    if 0 != os.path.getsize(args.file) > MAX_SIZE:
+        print(f"""The file you are trying to dump is larger than 1M.\n\
+        Actual size: {humanbytes(os.path.getsize(args.file))}\nrefusing to dump""")
+        sys.exit(2)
+    # print header
+    if args.chars:
+        print("Line      Data                                     Text")
+        print('=' * 68)
+    else:
+        print(f"Line      Data")
+        print('=' * 48)
+
+    # every line should contain 16 bytes, so we need a loop that get's 16 bytes
+    # and then works with them
+    next: bytes = bytes(16)
+    index: int = 0
+    while len(next) == 16:
+        next = file.read(16)
+        if len(next) == 0:
+            # no data left to read
+            break
+
+        line: str = f"{index:07x} | "
+
+        # actual hexdumping
+        for i in range(16):
+            if i % 2 == 0:
+                if len(next) > i+1:
+                    line += f"{next[i]:02x}{next[i+1]:02x} "
+                elif len(next) > i:
+                    line += f"{next[i]:02x}   "
+                else:
+                    line += "     "
+            else: continue
+
+        # if chars is enabled, print chars
+        if args.chars:
+            line += "| "
+            for b in next:
+                # special case for newline
+                if b == 0x0a:
+                    line+= '␤' # official unicode symbol representing newlines
+                # only print regular characters
+                elif b > 0x20 and b < 0x7e:
+                    line += chr(b)
+                elif b == 0x20:
+                    line += '\u2420'
+                else:
+                    line += '.'
+
+        print(line)
+        index += 16
+
+
+if __name__ == "__main__":
+    main()

src/tasks/hexdumper-a.py

@@ -1,8 +0,0 @@
-#!/usr/bin/env python3
-import sys
-
-def main():
-    # parse args
-
-if __name__ == "__main__":
-    main()