SOF-7915: refactor espresso regex schemas by pranabdas · Pull Request #4 · mat3ra/regex

pranabdas · 2026-06-08T12:26:36Z

No description provided.

timurbazhirov · 2026-06-19T02:59:08Z

@@ -0,0 +1,89 @@
+_fingerprints:


We should keep the version

timurbazhirov · 2026-06-19T03:01:06Z

    fs.writeFileSync(path.resolve(filePath), JSON.stringify(schema) + "\n", "utf8");
 }
+
+export function interpolatePrimitives(schema: any, primitives: Record<string, string>): any {


We can have this in utils

As these are used only build time, and not exported as runtime utility, we keep them here for now.

pranabdas · 2026-06-19T16:39:02Z

@@ -1 +1 @@
-{"applications":{"espresso":{"5.2.1":{"pw.x":{"_fingerprints":[{"regex":"^&control","flags":["g","i"],"isRequired":true},{"regex":"^&electrons","flags":["g","i"],"isRequired":true}],"control":{"_format":{"namelist":{"regex":"(\\$|&){{BLOCK_NAME}}\\n(?:\\s+[A-Za-z_]+\\s*=\\s*(?:['\"].*?['\"]|[^\\/\\n]+)(?:\\n\\s+[A-Za-z_]+\\s*=\\s*(?:['\"].*?['\"]|[^\\/\\n]+))*)?\\s*\\/","flags":["g","m"],"params":{"BLOCK_NAME":["CONTROL","ELECTRONS","IONS","CELL","SYSTEM"]}}},"calculation":{"regex":"calculation\\s*=\\s*'([^']+)'","flags":["g","m","i"]},"title":{"regex":"title\\s*=\\s*'([^']+)'","flags":["g","m","i"]},"restart_mode":{"regex":"restart_mode\\s*=\\s*'([^']+)'","flags":["g","m","i"]}}}},"7.1":{"pw.x":{"_fingerprints":[{"regex":"^&control","flags":["g","i"],"isRequired":true},{"regex":"^&electrons","flags":["g","i"],"isRequired":true}],"control":{"_format":{"namelist":{"regex":"(\\$|&){{BLOCK_NAME}}\\n(?:\\s+[A-Za-z_]+\\s*=\\s*(?:['\"].*?['\"]|[^\\/\\n]+)(?:\\n\\s+[A-Za-z_]+\\s*=\\s*(?:['\"].*?['\"]|[^\\/\\n]+))*)?\\s*\\/","flags":["g","m"],"params":{"BLOCK_NAME":["CONTROL","ELECTRONS","IONS","CELL","SYSTEM"]}}},"calculation":{"regex":"...","flags":["g","m","i"]}}}}}}}
+{"applications":{"espresso":{"5.2.1":{"pw.x":{"_fingerprints":[{"regex":"^&control","flags":["g","i"],"isRequired":true},{"regex":"^&electrons","flags":["g","i"],"isRequired":true}],"control":{"_format":{"namelist":{"regex":"(\\$|&)(CONTROL|ELECTRONS|IONS|CELL|SYSTEM)\\n(?:\\s+[A-Za-z_]+\\s*=\\s*(?:['\"].*?['\"]|[^\\/\\n]+)(?:\\n\\s+[A-Za-z_]+\\s*=\\s*(?:['\"].*?['\"]|[^\\/\\n]+))*)?\\s*\\/","flags":["g","m"],"params":{"BLOCK_NAME":["CONTROL","ELECTRONS","IONS","CELL","SYSTEM"]}}},"calculation":{"regex":"calculation\\s*=\\s*'([^']+)'","flags":["g","m","i"]},"title":{"regex":"title\\s*=\\s*'([^']+)'","flags":["g","m","i"]},"restart_mode":{"regex":"restart_mode\\s*=\\s*'([^']+)'","flags":["g","m","i"]}},"kv_pair":{"regex":"(\\w+)\\s*=\\s*([^,\\n/=]+)","flags":["g","i","m"]},"kv_pair_with_index":{"regex":"(\\w+)\\s*\\(\\s*(\\d+)\\s*\\)\\s*=\\s*([^,\\n/]+)","flags":["g","i","m"]},"namelist_block":{"regex":"&(CONTROL|SYSTEM|ELECTRONS|IONS|CELL|FCP|RISM)\\s*([\\s\\S]*?)\\/","flags":["i","m"],"params":{"BLOCK_NAME":["CONTROL","SYSTEM","ELECTRONS","IONS","CELL","FCP","RISM"]}},"cell_parameters_card":{"regex":"CELL_PARAMETERS\\s*[{(]?\\s*(alat|bohr|angstrom)?\\s*[)}]?\\s*\\n((?:[ \\t]*[-+]?(?:\\d+\\.\\d*|\\.\\d+|\\d+)(?:[eEdD][-+]?\\d+)?[ \\t]+[-+]?(?:\\d+\\.\\d*|\\.\\d+|\\d+)(?:[eEdD][-+]?\\d+)?[ \\t]+[-+]?(?:\\d+\\.\\d*|\\.\\d+|\\d+)(?:[eEdD][-+]?\\d+)?[ \\t]*\\n?){3})","flags":["i"],"params":{"UNIT":["alat","bohr","angstrom"]}},"atomic_positions_card":{"regex":"ATOMIC_POSITIONS\\s*[{(]?\\s*(alat|bohr|angstrom|crystal|crystal_sg)?\\s*[)}]?\\s*\\n((?:[ \\t]*\\w+(?:[ \\t]+[-+]?(?:\\d+\\.\\d*|\\.\\d+|\\d+)(?:[eEdD][-+]?\\d+)?){3}(?:(?:[ \\t]+[01]){3})?[ \\t]*\\n?)+)","flags":["i"],"params":{"UNIT":["alat","bohr","angstrom","crystal","crystal_sg"]}}}},"7.1":{"pw.x":{"_fingerprints":[{"regex":"^&control","flags":["g","i"],"isRequired":true},{"regex":"^&electrons","flags":["g","i"],"isRequired":true}],"control":{"_format":{"namelist":{"regex":"(\\$|&)(CONTROL|ELECTRONS|IONS|CELL|SYSTEM)\\n(?:\\s+[A-Za-z_]+\\s*=\\s*(?:['\"].*?['\"]|[^\\/\\n]+)(?:\\n\\s+[A-Za-z_]+\\s*=\\s*(?:['\"].*?['\"]|[^\\/\\n]+))*)?\\s*\\/","flags":["g","m"],"params":{"BLOCK_NAME":["CONTROL","ELECTRONS","IONS","CELL","SYSTEM"]}}},"calculation":{"regex":"calculation\\s*=\\s*'([^']+)'","flags":["g","m","i"]},"title":{"regex":"title\\s*=\\s*'([^']+)'","flags":["g","m","i"]},"restart_mode":{"regex":"restart_mode\\s*=\\s*'([^']+)'","flags":["g","m","i"]}},"kv_pair":{"regex":"(\\w+)\\s*=\\s*([^,\\n/=]+)","flags":["g","i","m"]},"kv_pair_with_index":{"regex":"(\\w+)\\s*\\(\\s*(\\d+)\\s*\\)\\s*=\\s*([^,\\n/]+)","flags":["g","i","m"]},"namelist_block":{"regex":"&(CONTROL|SYSTEM|ELECTRONS|IONS|CELL|FCP|RISM)\\s*([\\s\\S]*?)\\/","flags":["i","m"],"params":{"BLOCK_NAME":["CONTROL","SYSTEM","ELECTRONS","IONS","CELL","FCP","RISM"]}},"cell_parameters_card":{"regex":"CELL_PARAMETERS\\s*[{(]?\\s*(alat|bohr|angstrom)?\\s*[)}]?\\s*\\n((?:[ \\t]*[-+]?(?:\\d+\\.\\d*|\\.\\d+|\\d+)(?:[eEdD][-+]?\\d+)?[ \\t]+[-+]?(?:\\d+\\.\\d*|\\.\\d+|\\d+)(?:[eEdD][-+]?\\d+)?[ \\t]+[-+]?(?:\\d+\\.\\d*|\\.\\d+|\\d+)(?:[eEdD][-+]?\\d+)?[ \\t]*\\n?){3})","flags":["i"],"params":{"UNIT":["alat","bohr","angstrom"]}},"atomic_positions_card":{"regex":"ATOMIC_POSITIONS\\s*[{(]?\\s*(alat|bohr|angstrom|crystal|crystal_sg)?\\s*[)}]?\\s*\\n((?:[ \\t]*\\w+(?:[ \\t]+[-+]?(?:\\d+\\.\\d*|\\.\\d+|\\d+)(?:[eEdD][-+]?\\d+)?){3}(?:(?:[ \\t]+[01]){3})?[ \\t]*\\n?)+)","flags":["i"],"params":{"UNIT":["alat","bohr","angstrom","crystal","crystal_sg"]}}}}}}}


Maybe this should be further nested under /applications/espresso/5.2.1/pw.x/stdin.

timurbazhirov · 2026-06-23T02:38:00Z

+# regex keys above cannot match these because '(' follows the name instead of '='.
+kv_pair_with_index:
+  regex: '(\w+)\s*\(\s*(\d+)\s*\)\s*=\s*([^,\n/]+)'
+  flags: ["g", "i", "m"]


This and the above seem too generic to be included here

timurbazhirov · 2026-06-24T02:34:49Z

+      - IONS
+      - CELL
+      - FCP
+      - RISM


Let's try to reuse https://github.com/mat3ra/regex/blob/main/src/assets/file/fortran_namelist.yml#L19

pranabdas · 2026-06-25T01:53:35Z

-      - "CELL"
-      - "SYSTEM"
+    regex: !listToString
+      - '(\$|&){{BLOCK_NAME}}\s*\n'


$CONTROL is likely a legacy convention. Do we need to support it?

pranabdas added 25 commits June 8, 2026 20:07

define primitive regex

15fa170

do not trac tsc compiled .js scripts

c553e0f

combine different espresso versions together

a82f5d9

bump npm packages

1e0f525

bump github ci actions

1d6b1bc

fix tests

55e563b

fix linter

f266bd0

fix js test

80d3562

add regex for namelist block extraction

0f182d6

build a separate regex dict

1e03f6a

rename: NAMELIST_NAME -> BLOCK_NAME

5d6b06e

add possible namelist values

4738943

chore: revert espresso_namelist.yml file name

df612b6

include key value pair regex

43f0a6d

chore: comment

b96352f

add cell parameters regex

8f27c31

interpolate primitives build time

59b46ce

interpolate params build time + update tests

994cc93

chore: move fixture file

1f9deda

wrap regex parts in single quotes

8c2f2f2

add regex for atomic positions card

273d825

use more strict regex for optional constraints

6c0ea75

incorporate espresso regex dict to main pwin.yml

afbe476

put schemas under pwin

1292b88

update README

d000481

timurbazhirov reviewed Jun 19, 2026

View reviewed changes

pranabdas added 3 commits June 20, 2026 00:13

revert back to existing dir structure with multiple versions

632ebfa

chore: bump gh actions/checkout

f0d4be8

update README

15b02d0

inherit espresso v7.1 schema from v5.2.1

31a9365

pranabdas commented Jun 19, 2026

View reviewed changes

furter nest regex dicts to distinguish stdin and stdout regex

904e804

timurbazhirov reviewed Jun 23, 2026

View reviewed changes

pranabdas added 6 commits June 23, 2026 18:12

combine two float regex as same group

ede9e38

separate cell parameters row for reuse

b34f207

separate atomic positions row for reuse

1e8b932

individual capture groups for coordinates

94a1423

individual capture groups for cell parameters

e757ea4

chore: reorganize fixture file

8fd59fb

timurbazhirov reviewed Jun 24, 2026

View reviewed changes

pranabdas added 11 commits June 24, 2026 18:18

move kv pairs to separate partials.yml

200745c

consider quoted values in kv pair

3c6374a

reuse kv pairs in fortran namelist

83b1889

add missing namelists

274eb37

now that we have more strict namelist, remove namelist_block

6dba20f

add case insensitive flag for namelist

32780d2

move cell_parameters_row and atomic_positions_row to partials

c506183

add system namelist to stdin

b3d1450

remove namelist nesting, add electrons namelist, fix tests

b363cad

fix tests

21103aa

chore

a43962d

pranabdas commented Jun 25, 2026

View reviewed changes

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

SOF-7915: refactor espresso regex schemas#4

SOF-7915: refactor espresso regex schemas#4
pranabdas wants to merge 47 commits into
mainfrom
feat/SOF-7915

pranabdas commented Jun 8, 2026

Uh oh!

timurbazhirov Jun 19, 2026

Uh oh!

timurbazhirov Jun 19, 2026

Uh oh!

pranabdas Jun 24, 2026

Uh oh!

pranabdas Jun 19, 2026

Uh oh!

timurbazhirov Jun 23, 2026

Uh oh!

timurbazhirov Jun 24, 2026

Uh oh!

pranabdas Jun 25, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

		@@ -1 +1 @@
		{"applications":{"espresso":{"5.2.1":{"pw.x":{"_fingerprints":[{"regex":"^&control","flags":["g","i"],"isRequired":true},{"regex":"^&electrons","flags":["g","i"],"isRequired":true}],"control":{"_format":{"namelist":{"regex":"(\\$\|&){{BLOCK_NAME}}\\n(?:\\s+[A-Za-z_]+\\s=\\s(?:['\"].?['\"]\|[^\\/\\n]+)(?:\\n\\s+[A-Za-z_]+\\s=\\s(?:['\"].?['\"]\|[^\\/\\n]+)))?\\s\\/","flags":["g","m"],"params":{"BLOCK_NAME":["CONTROL","ELECTRONS","IONS","CELL","SYSTEM"]}}},"calculation":{"regex":"calculation\\s=\\s'([^']+)'","flags":["g","m","i"]},"title":{"regex":"title\\s=\\s'([^']+)'","flags":["g","m","i"]},"restart_mode":{"regex":"restart_mode\\s=\\s'([^']+)'","flags":["g","m","i"]}}}},"7.1":{"pw.x":{"_fingerprints":[{"regex":"^&control","flags":["g","i"],"isRequired":true},{"regex":"^&electrons","flags":["g","i"],"isRequired":true}],"control":{"_format":{"namelist":{"regex":"(\\$\|&){{BLOCK_NAME}}\\n(?:\\s+[A-Za-z_]+\\s=\\s(?:['\"].?['\"]\|[^\\/\\n]+)(?:\\n\\s+[A-Za-z_]+\\s=\\s(?:['\"].?['\"]\|[^\\/\\n]+)))?\\s\\/","flags":["g","m"],"params":{"BLOCK_NAME":["CONTROL","ELECTRONS","IONS","CELL","SYSTEM"]}}},"calculation":{"regex":"...","flags":["g","m","i"]}}}}}}}
		{"applications":{"espresso":{"5.2.1":{"pw.x":{"_fingerprints":[{"regex":"^&control","flags":["g","i"],"isRequired":true},{"regex":"^&electrons","flags":["g","i"],"isRequired":true}],"control":{"_format":{"namelist":{"regex":"(\\$\|&)(CONTROL\|ELECTRONS\|IONS\|CELL\|SYSTEM)\\n(?:\\s+[A-Za-z_]+\\s=\\s(?:['\"].?['\"]\|[^\\/\\n]+)(?:\\n\\s+[A-Za-z_]+\\s=\\s(?:['\"].?['\"]\|[^\\/\\n]+)))?\\s\\/","flags":["g","m"],"params":{"BLOCK_NAME":["CONTROL","ELECTRONS","IONS","CELL","SYSTEM"]}}},"calculation":{"regex":"calculation\\s=\\s'([^']+)'","flags":["g","m","i"]},"title":{"regex":"title\\s=\\s'([^']+)'","flags":["g","m","i"]},"restart_mode":{"regex":"restart_mode\\s=\\s'([^']+)'","flags":["g","m","i"]}},"kv_pair":{"regex":"(\\w+)\\s=\\s([^,\\n/=]+)","flags":["g","i","m"]},"kv_pair_with_index":{"regex":"(\\w+)\\s\\(\\s(\\d+)\\s\\)\\s=\\s([^,\\n/]+)","flags":["g","i","m"]},"namelist_block":{"regex":"&(CONTROL\|SYSTEM\|ELECTRONS\|IONS\|CELL\|FCP\|RISM)\\s([\\s\\S]?)\\/","flags":["i","m"],"params":{"BLOCK_NAME":["CONTROL","SYSTEM","ELECTRONS","IONS","CELL","FCP","RISM"]}},"cell_parameters_card":{"regex":"CELL_PARAMETERS\\s[{(]?\\s(alat\|bohr\|angstrom)?\\s[)}]?\\s\\n((?:[ \\t][-+]?(?:\\d+\\.\\d\|\\.\\d+\|\\d+)(?:[eEdD][-+]?\\d+)?[ \\t]+[-+]?(?:\\d+\\.\\d\|\\.\\d+\|\\d+)(?:[eEdD][-+]?\\d+)?[ \\t]+[-+]?(?:\\d+\\.\\d\|\\.\\d+\|\\d+)(?:[eEdD][-+]?\\d+)?[ \\t]\\n?){3})","flags":["i"],"params":{"UNIT":["alat","bohr","angstrom"]}},"atomic_positions_card":{"regex":"ATOMIC_POSITIONS\\s[{(]?\\s(alat\|bohr\|angstrom\|crystal\|crystal_sg)?\\s[)}]?\\s\\n((?:[ \\t]\\w+(?:[ \\t]+[-+]?(?:\\d+\\.\\d\|\\.\\d+\|\\d+)(?:[eEdD][-+]?\\d+)?){3}(?:(?:[ \\t]+[01]){3})?[ \\t]\\n?)+)","flags":["i"],"params":{"UNIT":["alat","bohr","angstrom","crystal","crystal_sg"]}}}},"7.1":{"pw.x":{"_fingerprints":[{"regex":"^&control","flags":["g","i"],"isRequired":true},{"regex":"^&electrons","flags":["g","i"],"isRequired":true}],"control":{"_format":{"namelist":{"regex":"(\\$\|&)(CONTROL\|ELECTRONS\|IONS\|CELL\|SYSTEM)\\n(?:\\s+[A-Za-z_]+\\s=\\s(?:['\"].?['\"]\|[^\\/\\n]+)(?:\\n\\s+[A-Za-z_]+\\s=\\s(?:['\"].?['\"]\|[^\\/\\n]+)))?\\s\\/","flags":["g","m"],"params":{"BLOCK_NAME":["CONTROL","ELECTRONS","IONS","CELL","SYSTEM"]}}},"calculation":{"regex":"calculation\\s=\\s'([^']+)'","flags":["g","m","i"]},"title":{"regex":"title\\s=\\s'([^']+)'","flags":["g","m","i"]},"restart_mode":{"regex":"restart_mode\\s=\\s'([^']+)'","flags":["g","m","i"]}},"kv_pair":{"regex":"(\\w+)\\s=\\s([^,\\n/=]+)","flags":["g","i","m"]},"kv_pair_with_index":{"regex":"(\\w+)\\s\\(\\s(\\d+)\\s\\)\\s=\\s([^,\\n/]+)","flags":["g","i","m"]},"namelist_block":{"regex":"&(CONTROL\|SYSTEM\|ELECTRONS\|IONS\|CELL\|FCP\|RISM)\\s([\\s\\S]?)\\/","flags":["i","m"],"params":{"BLOCK_NAME":["CONTROL","SYSTEM","ELECTRONS","IONS","CELL","FCP","RISM"]}},"cell_parameters_card":{"regex":"CELL_PARAMETERS\\s[{(]?\\s(alat\|bohr\|angstrom)?\\s[)}]?\\s\\n((?:[ \\t][-+]?(?:\\d+\\.\\d\|\\.\\d+\|\\d+)(?:[eEdD][-+]?\\d+)?[ \\t]+[-+]?(?:\\d+\\.\\d\|\\.\\d+\|\\d+)(?:[eEdD][-+]?\\d+)?[ \\t]+[-+]?(?:\\d+\\.\\d\|\\.\\d+\|\\d+)(?:[eEdD][-+]?\\d+)?[ \\t]\\n?){3})","flags":["i"],"params":{"UNIT":["alat","bohr","angstrom"]}},"atomic_positions_card":{"regex":"ATOMIC_POSITIONS\\s[{(]?\\s(alat\|bohr\|angstrom\|crystal\|crystal_sg)?\\s[)}]?\\s\\n((?:[ \\t]\\w+(?:[ \\t]+[-+]?(?:\\d+\\.\\d\|\\.\\d+\|\\d+)(?:[eEdD][-+]?\\d+)?){3}(?:(?:[ \\t]+[01]){3})?[ \\t]\\n?)+)","flags":["i"],"params":{"UNIT":["alat","bohr","angstrom","crystal","crystal_sg"]}}}}}}}

Uh oh!

Conversation

pranabdas commented Jun 8, 2026

Uh oh!

timurbazhirov Jun 19, 2026

Choose a reason for hiding this comment

Uh oh!

timurbazhirov Jun 19, 2026

Choose a reason for hiding this comment

Uh oh!

pranabdas Jun 24, 2026

Choose a reason for hiding this comment

Uh oh!

pranabdas Jun 19, 2026

Choose a reason for hiding this comment

Uh oh!

timurbazhirov Jun 23, 2026

Choose a reason for hiding this comment

Uh oh!

timurbazhirov Jun 24, 2026

Choose a reason for hiding this comment

Uh oh!

pranabdas Jun 25, 2026

Choose a reason for hiding this comment

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants