From b3f9d3af9b87828b46c436b026d18122820fc74c Mon Sep 17 00:00:00 2001
From: Trilarion <Trilarion@users.noreply.github.com>
Date: Wed, 2 Sep 2020 22:31:01 +0200
Subject: [PATCH] grammars for entries parsing now LALR(1), which is much
 faster

---
 code/grammar_entries.lark                     | 33 ++++----
 code/grammar_listing.lark                     | 29 ++++---
 code/maintenance_collect_inspiration_infos.py |  9 ++-
 code/utils/constants.py                       |  6 +-
 code/utils/osg.py                             | 80 ++++++++++++++++++-
 entries/0_ad.md                               |  2 +-
 entries/2048.md                               |  2 +-
 entries/abes_amazing_adventure.md             |  2 +-
 entries/achtung_die_kurve.md                  |  3 +-
 entries/aisleriot.md                          |  2 +-
 entries/battles_of_antargis.md                |  6 +-
 entries/netacka.md                            |  3 +-
 entries/pyglet.md                             |  2 +-
 entries/star-wars-iii.md                      |  5 +-
 entries/survivor.md                           |  3 +-
 entries/thiefcatcher.md                       |  3 +-
 entries/zatacka.md                            |  3 +-
 entries/zatacka_x.md                          |  3 +-
 18 files changed, 147 insertions(+), 49 deletions(-)

diff --git a/code/grammar_entries.lark b/code/grammar_entries.lark
index 59fc239f..18d23339 100644
--- a/code/grammar_entries.lark
+++ b/code/grammar_entries.lark
@@ -1,21 +1,26 @@
-start: title description property+ (_E note)? _E building
+start: title description property+ note? building
+title: "#" /(?! ).+(?<! )/ _NL                 // not starting or ending with a space
 
-title: "#" /(?! ).+(?<! )/ "\n" _E                 // not starting or ending with a space
+description: "_" /(?! ).+(?<![ _])/ "_" _NL       // single line not ending with underscore
+property: "-" _key ":" _values _NL
+_key : /(?! ).+?(?=:)(?<! )/    // key: everything until next ":", not beginning or ending with a space
+_values : [_value ("," _value)*]
+_value : quoted_value | unquoted_value
+quoted_value : /\".+?\"/   // with quotation marks, can contain commas
+unquoted_value : /(?![ \"])[^,\n]+(?<![ \"])/ // cannot contain commas, cannot start or end with quotation mark
 
-description: "_" /(?! ).+(?<![ _])/ "_\n" _E        // single line not ending with underscore
+note.3: /(?![\-#]).*\n/+                              // Unstructured text, not starting with - or #
 
-note: /(?![\-#]).*\n/*                              // Unstructured text, not starting with - or #
+building: "## Building" _NL property* note?     // the "building" section
 
-building: "## Building\n" (_E property+)? (_E note)?     // the "building" section
 
-property: "-" _key ":" _values "\n"?                // a property on a single line "- key: value"
-_key: /(?! ).+?(?=:)(?<! )/                         // key: everything until next ":", not beginning or ending with a space
-_values: [_value ("," _value)*]                     // a comma separated list
-_value: quoted_value | unquoted_value               // quoted or unquoted values
-quoted_value: /\".+?\"/                             // with quotation marks, can contain commas
-unquoted_value: /(?![ \"])[^,\n]+(?<![ ])/        // cannot contain commas, cannot start or end with quotation mark
+_NUMBER: /[0-9]+/
 
-_E: /^$\n/m                                         // empty new line
+CR : /\r/
+LF : /\n/
+_NL : CR? LF
+WS : (" "|/\t/)+
+_EL.2 : /^$\n/m
 
-%import common.WS
-%ignore WS
\ No newline at end of file
+%ignore WS
+%ignore _EL
diff --git a/code/grammar_listing.lark b/code/grammar_listing.lark
index 8a8cdf2e..a8b19e10 100644
--- a/code/grammar_listing.lark
+++ b/code/grammar_listing.lark
@@ -1,18 +1,23 @@
-start: entry*
-entry: "##" name "[" _NUMBER "]\n" property+
-property: "-" _key ":" _values "\n"
-_key: /(?! ).+?(?=:)(?<! )/    // key: everything until next ":", not beginning or ending with a space
-_values: [_value ("," _value)*]
-_value: quoted_value | unquoted_value
-quoted_value: /\".+?\"/   // with quotation marks, can contain commas
-unquoted_value: /(?![ \"])[^,\n]+(?<![ \"])/ // cannot contain commas, cannot start or end with quotation mark
+start: _COMMENT _HEADER entry*
+entry: "##" name "[" _NUMBER "]" _NL property+
+property: "-" _key ":" _values _NL
+_key : /(?! ).+?(?=:)(?<! )/    // key: everything until next ":", not beginning or ending with a space
+_values : [_value ("," _value)*]
+_value : quoted_value | unquoted_value
+quoted_value : /\".+?\"/   // with quotation marks, can contain commas
+unquoted_value : /(?![ \"])[^,\n]+(?<![ \"])/ // cannot contain commas, cannot start or end with quotation mark
 
 name: /(?! ).+?(?= \[)/    // developer name: everything until " ["
 
 _NUMBER: /[0-9]+/
 
-%import common.WS
+CR : /\r/
+LF : /\n/
+_NL : CR? LF
+WS : (" "|/\t/)+
+_EL : /^$\n/m
+_COMMENT : /^\[comment\]: #.*$\n/m   // [comment]: # xxx
+_HEADER : /^# .+$\n/m
+
 %ignore WS
-%ignore /^\[comment\]: #.*$\n/m   // [comment]: # xxx
-%ignore /^# .+$\n/m    // the line starting with "# "
-%ignore /^$\n/m        // empty lines
+%ignore _EL
diff --git a/code/maintenance_collect_inspiration_infos.py b/code/maintenance_collect_inspiration_infos.py
index 8cc32d6c..6a82da6b 100644
--- a/code/maintenance_collect_inspiration_infos.py
+++ b/code/maintenance_collect_inspiration_infos.py
@@ -2,6 +2,7 @@
 Maintenance of inspirations.md and synchronization with the inspirations in the entries.
 """
 
+import time
 from utils import constants as c, utils, osg, osg_ui
 
 
@@ -33,8 +34,14 @@ if __name__ == "__main__":
 
 
     # assemble info
+    t0 = time.process_time()
     entries = osg.read_entries()
-    entries = osg.assemble_infos()
+    print('took {}s'.format(time.process_time()-t0))
+    t0 = time.process_time()
+    # entries = osg.assemble_infos()
+    osg.write_entries(entries)
+    print('took {}s'.format(time.process_time()-t0))
+
 
     # assemble inspirations info from entries
     entries_inspirations = {}
diff --git a/code/utils/constants.py b/code/utils/constants.py
index ffd3c551..fa9879b4 100644
--- a/code/utils/constants.py
+++ b/code/utils/constants.py
@@ -37,8 +37,10 @@ essential_fields = ('Home', 'State', 'Keywords', 'Code repository', 'Code langua
 
 # only these fields can be used currently (in this order)
 valid_fields = (
-    'Home', 'Media', 'State', 'Play', 'Download', 'Platform', 'Keywords', 'Code repository', 'Code language',
-    'Code license', 'Code dependencies', 'Assets license', 'Developer', 'Build system', 'Build instructions')
+    'Home', 'Media', 'Inspirations', 'State', 'Play', 'Download', 'Platform', 'Keywords', 'Code repository', 'Code language',
+    'Code license', 'Code dependencies', 'Assets license', 'Developer')
+
+valid_building_fields = ('Build system', 'Build instructions')
 
 # these are the only valid platforms currently (and must be given in this order)
 valid_platforms = ('Windows', 'Linux', 'macOS', 'Android', 'iOS', 'Web')
diff --git a/code/utils/osg.py b/code/utils/osg.py
index 9abf14ee..16a76dc8 100644
--- a/code/utils/osg.py
+++ b/code/utils/osg.py
@@ -86,7 +86,7 @@ class EntryTransformer(lark.Transformer):
         """
         if not x:
             raise lark.Discard
-        return 'note', x[0].value
+        return 'note', ''.join((x.value for x in x))
 
     def building(self, x):
         d = {}
@@ -401,7 +401,7 @@ def read_and_parse(content_file: str, grammar_file: str, transformer: lark.Trans
     """
     content = utils.read_text(content_file)
     grammar = utils.read_text(grammar_file)
-    parser = lark.Lark(grammar, debug=False)
+    parser = lark.Lark(grammar, debug=False, parser='lalr')
     tree = parser.parse(content)
     return transformer.transform(tree)
 
@@ -565,7 +565,7 @@ def read_entries():
     # setup parser
     grammar_file = os.path.join(code_path, 'grammar_entries.lark')
     grammar = utils.read_text(grammar_file)
-    parser = lark.Lark(grammar, debug=False)
+    parser = lark.Lark(grammar, debug=False, parser='lalr')
 
     # setup transformer
     transformer = EntryTransformer()
@@ -576,16 +576,20 @@ def read_entries():
     # iterate over all entries
     for file, _, content in entry_iterator():
 
-        print(file)
+        if not content.endswith('\n'):
+            content += '\n'
 
         # parse and transform entry content
         try:
             tree = parser.parse(content)
             entry = transformer.transform(tree)
         except Exception as e:
+            print(file)
             print(e)
             continue
 
+        # TODO check entry
+
         # add file information
         entry['file'] = file
 
@@ -594,6 +598,74 @@ def read_entries():
 
     return entries
 
+def write_entries(entries):
+    """
+
+    :return:
+    """
+
+    # iterate over all entries
+    entries = entries[:20]
+    for entry in entries:
+        write_entry(entry)
+
+def write_entry(entry):
+    """
+
+    :param entry:
+    :return:
+    """
+    # TODO check entry
+
+    # get path
+    entry_path = os.path.join(entries_path, entry['file'])
+
+    # create output content
+    content = create_entry_content(entry)
+
+    # write entry
+    utils.write_text(entry_path, content)
+
+
+def create_entry_content(entry):
+    """
+
+    :param entry:
+    :return:
+    """
+
+    # title and description
+    content = '# {}\n\n_{}_\n\n'.format(entry['title'], entry['description'])
+
+    # now properties in the recommended order
+    for field in valid_fields:
+        field_name = field.lower()
+        if field_name in entry:
+            content += '- {}: {}\n'.format(field, ', '.join(entry[field_name]))
+    content += '\n'
+
+    # if there is a note, insert it
+    if 'note' in entry:
+        content += entry['note'] + '\n'
+
+    # building header
+    content += '## Building\n\n'
+
+    # building properties if present
+    has_properties = False
+    for field in valid_building_fields:
+        field_name = field.lower()
+        if field_name in entry['building']:
+            has_properties = True
+            content += '- {}: {}\n'.format(field, ', '.join(entry['building'][field_name]))
+
+    # if there is a note, insert it
+    if 'note' in entry['building']:
+        if has_properties:
+            content += '\n'
+        content += entry['building']['note'] + '\n'
+
+    return content
 
 def compare_entries_developers(entries, developers):
     """
diff --git a/entries/0_ad.md b/entries/0_ad.md
index e3b2859d..ae0760eb 100644
--- a/entries/0_ad.md
+++ b/entries/0_ad.md
@@ -1,6 +1,6 @@
 # 0 A.D.
 
-_0 A.D. is a free, open-source, cross-platform real-time strategy game._
+_Real-time strategy game._
 
 - Home: https://play0ad.com/, https://sourceforge.net/projects/zero-ad/
 - Media: <https://en.wikipedia.org/wiki/0_A.D._(video_game)>
diff --git a/entries/2048.md b/entries/2048.md
index af16b05a..343ed8b0 100644
--- a/entries/2048.md
+++ b/entries/2048.md
@@ -17,4 +17,4 @@ Port to Android: https://github.com/tpcstld/2048
 
 ## Building
 
-- Build system: Rake
\ No newline at end of file
+- Build system: Rake
diff --git a/entries/abes_amazing_adventure.md b/entries/abes_amazing_adventure.md
index 408dc72b..fb6e6fc5 100644
--- a/entries/abes_amazing_adventure.md
+++ b/entries/abes_amazing_adventure.md
@@ -15,4 +15,4 @@ _Side scrolling platform game._
 
 ## Building
 
-- Build system: Autoconf
\ No newline at end of file
+- Build system: Autoconf
diff --git a/entries/achtung_die_kurve.md b/entries/achtung_die_kurve.md
index d5d7cbdc..47c1bbf4 100644
--- a/entries/achtung_die_kurve.md
+++ b/entries/achtung_die_kurve.md
@@ -3,10 +3,11 @@
 _Clone of Achtung, die Kurve!, a simple skill game._
 
 - Home: https://kurve.se/
+- Inspirations: "Achtung, die Kurve!"
 - State: mature
 - Play: https://kurve.se/
 - Platform: Web
-- Keywords: action, clone, inspired by "Achtung, die Kurve!", multiplayer local, open content
+- Keywords: action, clone, multiplayer local, open content
 - Code repository: https://github.com/SimonAlling/kurve.git
 - Code language: JavaScript
 - Code license: AGPL-3.0
diff --git a/entries/aisleriot.md b/entries/aisleriot.md
index 3ad76287..4f373ab7 100644
--- a/entries/aisleriot.md
+++ b/entries/aisleriot.md
@@ -14,4 +14,4 @@ _Collection of patience games._
 
 ## Building
 
-- Build system: Make
\ No newline at end of file
+- Build system: Make
diff --git a/entries/battles_of_antargis.md b/entries/battles_of_antargis.md
index e35e9e4a..deb78e9d 100644
--- a/entries/battles_of_antargis.md
+++ b/entries/battles_of_antargis.md
@@ -1,10 +1,10 @@
 # Battles of Antargis
 
-_A real-time-strategy (RTS) game, which is a mixture of 3 three games: Powermonger, Settlers, Warcraft._
+_A real-time-strategy (RTS) game._
 
-- Home: https://plus.google.com/101003433246259562872, 
+- Home: https://plus.google.com/101003433246259562872
 - State: beta, inactive since 2014
-- Keywords: strategy
+- Keywords: strategy, inspired by Powermonger + Settlers + Warcraft
 - Code repository: https://github.com/godrin/antargis.git
 - Code language: C, C++
 - Code license: GPL-2.0
diff --git a/entries/netacka.md b/entries/netacka.md
index 67e3c804..549ea1dc 100644
--- a/entries/netacka.md
+++ b/entries/netacka.md
@@ -3,8 +3,9 @@
 _Remake of Achtung, die Kurve!._
 
 - Home: https://pwmarcz.pl/netacka/
+- Inspirations: "Achtung, die Kurve!"
 - State: mature
-- Keywords: remake, inspired by "Achtung, die Kurve!", skill
+- Keywords: remake, skill
 - Code repository: https://github.com/pwmarcz/netacka.git
 - Code language: C
 - Code license: MIT
diff --git a/entries/pyglet.md b/entries/pyglet.md
index 009ecfbc..7b083c47 100644
--- a/entries/pyglet.md
+++ b/entries/pyglet.md
@@ -2,7 +2,7 @@
 
 _Multimedia library for Python._
 
-- Home: http://pyglet.org/,
+- Home: http://pyglet.org/
 - State: mature
 - Download: https://pypi.org/project/pyglet/
 - Platform: Windows, Linux, macOS
diff --git a/entries/star-wars-iii.md b/entries/star-wars-iii.md
index 55a70c36..d4d48e8c 100644
--- a/entries/star-wars-iii.md
+++ b/entries/star-wars-iii.md
@@ -1,10 +1,11 @@
 # Star-Wars-III
 
-_Remake of Star Wars (1983 arcade game)._
+_Remake of Star Wars (1983) arcade game._
 
 - Home: https://github.com/abhinandanramesh/Star-Wars-III
+- Inspirations: Star Wars (1983 arcade game)
 - State: mature, inactive since 2014
-- Keywords: arcade, inspired by "Star Wars (1983 arcade game)", remake, skill
+- Keywords: arcade, remake, skill
 - Code repository: https://github.com/abhinandanramesh/Star-Wars-III.git
 - Code language: Python
 - Code license: GPL-2.0
diff --git a/entries/survivor.md b/entries/survivor.md
index 5c35714d..215b691d 100644
--- a/entries/survivor.md
+++ b/entries/survivor.md
@@ -3,10 +3,11 @@
 _Remake of Survivor (1986)._
 
 - Home: http://www.schillmania.com/survivor/
+- Inspirations: Survivor (1986)
 - State: mature
 - Play: http://www.schillmania.com/survivor/
 - Platform: Web
-- Keywords: remake, inspired by "Survivor (1986)"
+- Keywords: remake
 - Code repository: https://github.com/scottschiller/SURVIVOR.git
 - Code language: JavaScript
 - Code license: CC-BY-NC-3.0
diff --git a/entries/thiefcatcher.md b/entries/thiefcatcher.md
index 72b2ff97..53e1e376 100644
--- a/entries/thiefcatcher.md
+++ b/entries/thiefcatcher.md
@@ -4,8 +4,9 @@ _Remake of Where in the World Is Carmen Sandiego? (1985)._
 
 - Home: https://github.com/Ponup/thiefcatcher
 - Media: <https://en.wikipedia.org/wiki/Where_in_the_World_Is_Carmen_Sandiego%3F_(1985_video_game)>
+- Inspirations: Where in the World Is Carmen Sandiego? (1985)
 - State: beta
-- Keywords: strategy, educational, inspired by "Where in the World Is Carmen Sandiego? (1985)", remake
+- Keywords: strategy, educational, remake
 - Code repository: https://github.com/Ponup/thiefcatcher.git
 - Code language: C++
 - Code license: GPL-3.0
diff --git a/entries/zatacka.md b/entries/zatacka.md
index f887fd6d..5535e207 100644
--- a/entries/zatacka.md
+++ b/entries/zatacka.md
@@ -3,10 +3,11 @@
 _Remake of a 2D multiplayer game similar to the Tron movie-themed light cycle games and snake games._
 
 - Home: http://zatacka.sourceforge.net/, https://sourceforge.net/projects/zatacka/
+- Inspirations: "Achtung, die Kurve!"
 - State: beta, inactive since 2007
 - Download: http://zatacka.sourceforge.net/index.php?id=download, https://sourceforge.net/projects/zatacka/files/
 - Platform: Windows, Linux
-- Keywords: arcade, 2D, inspired by "Achtung, die Kurve!", multiplayer
+- Keywords: arcade, 2D, multiplayer
 - Code repository: http://zatacka.cvs.sourceforge.net (cvs)
 - Code language: C, C++
 - Code license: GPL-2.0
diff --git a/entries/zatacka_x.md b/entries/zatacka_x.md
index 57227426..2513c6f6 100644
--- a/entries/zatacka_x.md
+++ b/entries/zatacka_x.md
@@ -3,8 +3,9 @@
 _Remake of Achtung, die Kurve!._
 
 - Home: https://github.com/simenheg/zatackax
+- Inspirations: "Achtung, die Kurve!"
 - State: beta
-- Keywords: action, inspired by "Achtung, die Kurve!", remake
+- Keywords: action, remake
 - Code repository: https://github.com/simenheg/zatackax.git
 - Code language: C
 - Code license: GPL-3.0