chore: fully automatic table generation

The codec table is now created fully automatically. You just need
to run a single script. The script is written in Python in hope
that it can be adapted to be used for other multicodec implementations
as well. Python is most likely installed on all systems and no
big toolchain is needed in order to run/modify it.

This commit also updates the table to the most current version.

BREAKING CHANGE: multibase is not part of this package anymore

As multibase works differently from multicodec, those codecs
were [removed from the multicodec table], hence those are also
removed from this implementation as we have automatic
conversion from the upstream table.

[removed from the multicodec table]:
multiformats/multicodec@1ec0e97

README.md

@@ -51,16 +51,11 @@ https://multiformats.github.io/js-multicodec/
 
 ## Updating the lookup table
 
-Updating the lookup table is a manual process. The source of truth is the
-[multicodec default table](https://github.com/multiformats/multicodec/blob/master/table.csv). To make the process easier, there’s an [AWK script in the tools directory](tools/update-table.awk) that does a basic conversion of the default table. The result can’t be used as-is, but serves as a template for manual diffing. The workflow is:
+Updating the lookup table is done with a script. The source of truth is the
+[multicodec default table](https://github.com/multiformats/multicodec/blob/master/table.csv).
+Update the table with running:
 
- - Create a basic draft version
-
-    `curl -X GET https://raw.githubusercontent.com/multiformats/multicodec/master/table.csv|awk -f tools/update-table.awk > /tmp/draft.js`
-
- - Diff it with your tool of choice (e.g. [Meld](http://meldmerge.org/)) and apply the changes
-
-     `meld /tmp/draft.js base-table.js`
+    curl -X GET https://raw.githubusercontent.com/multiformats/multicodec/master/table.csv|./tools/update-table.py
 
 ## Contribute
 

src/base-table.js

@@ -1,33 +1,27 @@
+// THIS FILE IS GENERATED, DO NO EDIT MANUALLY
+// For more information see the README.md
+/* eslint-disable dot-notation */
 'use strict'
 
-// spec and table at: https://github.com/multiformats/multicodec
-
-exports = module.exports
-
-// Miscellaneous
+// miscellaneous
 exports['raw'] = Buffer.from('55', 'hex')
 
-// bases encodings
-exports['base1'] = Buffer.from('01', 'hex')
-exports['base2'] = Buffer.from('00', 'hex')
-exports['base8'] = Buffer.from('07', 'hex')
-exports['base10'] = Buffer.from('09', 'hex')
-
-// Serialization formats
+// serialization formats
 exports['cbor'] = Buffer.from('51', 'hex')
 exports['protobuf'] = Buffer.from('50', 'hex')
 exports['rlp'] = Buffer.from('60', 'hex')
 exports['bencode'] = Buffer.from('63', 'hex')
 
-// Multiformats
+// multiformats
 exports['multicodec'] = Buffer.from('30', 'hex')
 exports['multihash'] = Buffer.from('31', 'hex')
 exports['multiaddr'] = Buffer.from('32', 'hex')
 exports['multibase'] = Buffer.from('33', 'hex')
-exports['md4'] = Buffer.from('d4', 'hex')
-exports['md5'] = Buffer.from('d5', 'hex')
 
 // multihashes
+exports['identity'] = Buffer.from('00', 'hex')
+exports['md4'] = Buffer.from('d4', 'hex')
+exports['md5'] = Buffer.from('d5', 'hex')
 exports['sha1'] = Buffer.from('11', 'hex')
 exports['sha2-256'] = Buffer.from('12', 'hex')
 exports['sha2-512'] = Buffer.from('13', 'hex')
@@ -376,32 +370,37 @@ exports['dccp'] = Buffer.from('21', 'hex')
 exports['sctp'] = Buffer.from('84', 'hex')
 exports['udt'] = Buffer.from('012d', 'hex')
 exports['utp'] = Buffer.from('012e', 'hex')
+exports['p2p'] = Buffer.from('01a5', 'hex')
 exports['ipfs'] = Buffer.from('01a5', 'hex')
 exports['http'] = Buffer.from('01e0', 'hex')
 exports['https'] = Buffer.from('01bb', 'hex')
 exports['quic'] = Buffer.from('01cc', 'hex')
 exports['ws'] = Buffer.from('01dd', 'hex')
+exports['wss'] = Buffer.from('01de', 'hex')
 exports['onion'] = Buffer.from('01bc', 'hex')
 exports['onion3'] = Buffer.from('01bd', 'hex')
 exports['garlic64'] = Buffer.from('01be', 'hex')
 exports['p2p-circuit'] = Buffer.from('0122', 'hex')
+exports['dns'] = Buffer.from('35', 'hex')
 exports['dns4'] = Buffer.from('36', 'hex')
 exports['dns6'] = Buffer.from('37', 'hex')
 exports['dnsaddr'] = Buffer.from('38', 'hex')
+exports['p2p-websocket-star'] = Buffer.from('01df', 'hex')
+exports['p2p-webrtc-star'] = Buffer.from('0113', 'hex')
+exports['p2p-webrtc-direct'] = Buffer.from('0114', 'hex')
+exports['unix'] = Buffer.from('0190', 'hex')
 
 // archiving formats
 
 // image formats
 
 // video formats
 
-// VCS formats
-exports['git-raw'] = Buffer.from('78', 'hex')
-
 // IPLD formats
 exports['dag-pb'] = Buffer.from('70', 'hex')
 exports['dag-cbor'] = Buffer.from('71', 'hex')
 exports['dag-json'] = Buffer.from('0129', 'hex')
+exports['git-raw'] = Buffer.from('78', 'hex')
 exports['eth-block'] = Buffer.from('90', 'hex')
 exports['eth-block-list'] = Buffer.from('91', 'hex')
 exports['eth-tx-trie'] = Buffer.from('92', 'hex')
@@ -411,7 +410,6 @@ exports['eth-tx-receipt'] = Buffer.from('95', 'hex')
 exports['eth-state-trie'] = Buffer.from('96', 'hex')
 exports['eth-account-snapshot'] = Buffer.from('97', 'hex')
 exports['eth-storage-trie'] = Buffer.from('98', 'hex')
-
 exports['bitcoin-block'] = Buffer.from('b0', 'hex')
 exports['bitcoin-tx'] = Buffer.from('b1', 'hex')
 exports['zcash-block'] = Buffer.from('c0', 'hex')
@@ -422,7 +420,6 @@ exports['decred-block'] = Buffer.from('e0', 'hex')
 exports['decred-tx'] = Buffer.from('e1', 'hex')
 exports['dash-block'] = Buffer.from('f0', 'hex')
 exports['dash-tx'] = Buffer.from('f1', 'hex')
-
 exports['torrent-info'] = Buffer.from('7b', 'hex')
 exports['torrent-file'] = Buffer.from('7c', 'hex')
 exports['ed25519-pub'] = Buffer.from('ed', 'hex')

tools/update-table.py

@@ -0,0 +1,62 @@
+#!/usr/bin/env python3
+
+import csv
+import os
+import sys
+
+# This is relative to where this script resides. Though you can also define
+# an absolute path
+DEFAULT_OUTPUT_DIR = '../src'
+
+# The header of the generated files
+HEADER = '''\
+// THIS FILE IS GENERATED, DO NO EDIT MANUALLY
+// For more information see the README.md
+/* eslint-disable dot-notation */
+'use strict'
+'''
+
+def padded_hex(hexstring):
+    """Creates a padded (starting with a 0 if odd) hex string"""
+    number = int(row['code'], 16)
+    hexbytes = '{:x}'.format(number)
+    if len(hexbytes) % 2:
+        prefix = '0x0'
+    else:
+        prefix = '0x'
+    return prefix + hexbytes
+
+
+parsed = []
+multicodec_reader = csv.DictReader(sys.stdin, skipinitialspace=True)
+for row in multicodec_reader:
+    # Skip over headlines and not yet defined codes
+    if row['code'] and row['code'] != '0x':
+        code = padded_hex(row['code'])
+        name_const = row['codec'].upper().replace('-', '_')
+        name_human = row['codec']
+        parsed.append({
+            'const': name_const,
+            'human': name_human,
+            'code': code,
+        })
+    # add headlines
+    if row['codec'] and not row['description'] and not row['code']:
+        parsed.append({
+            'headline': row['codec']
+        })
+
+tools_dir = os.path.dirname(os.path.abspath(__file__))
+output_dir = os.path.join(tools_dir, DEFAULT_OUTPUT_DIR)
+
+print_file = os.path.join(output_dir, 'base-table.js')
+with open(print_file, 'w') as ff:
+    ff.write(HEADER)
+    for index, codec in enumerate(parsed):
+        if 'headline' in codec:
+            ff.write("\n// {headline}\n".format(**codec))
+        else:
+            # print('{} {} {:02x}'.format(codec['human'], codec['code'], codec['code']))
+            hexstring = codec['code'][2:]
+            ff.write("exports['{}'] = Buffer.from('{}', 'hex')\n"
+                     .format(codec['human'], hexstring))