Skip to content

Fix ADF15 parser and refine regex patterns #497

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
munechika-koyo wants to merge 4 commits into
base: development
Choose a base branch
from
+23 −14
Open

Fix ADF15 parser and refine regex patterns #497

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
234ec15
Fix ADF15 parser
munechika-koyo Mar 11, 2026
b2cdca5
Fix regressions for config regex pattern in _scrape_metadata_full
munechika-koyo Mar 11, 2026
6157a17
Move regex pattern definition out of for-loop
munechika-koyo Mar 21, 2026
04ddbd7
Refine regex pattern for configuration string in _scrape_metadata_full
munechika-koyo Mar 22, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
37 changes: 23 additions & 14 deletions cherab/openadas/parse/adf15.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,6 +38,13 @@
11: 'O',
12: 'Q',
13: 'R',
14: 'T',
15: 'U',
16: 'V',
17: 'W',
18: 'X',
19: 'Y',
20: 'Z',
}


Expand Down Expand Up @@ -109,9 +116,8 @@ def _scrape_metadata_hydrogen(file, element, charge):
lines.pop(0)
index_lines = lines

pec_hydrogen_transition_match = r'^C\s*([0-9]*)\.\s*([0-9]*\.[0-9]*)\s*N=\s*([0-9]*) - N=\s*([0-9]*)\s*([A-Z]*)'
for i in range(len(index_lines)):

pec_hydrogen_transition_match = r'^C\s*([0-9]*)\.\s*([0-9]*\.[0-9]*)\s*N=\s*([0-9]*) - N=\s*([0-9]*)\s*([A-Z]*)'
match = re.match(pec_hydrogen_transition_match, index_lines[i], re.IGNORECASE)
if not match:
continue
Expand All @@ -120,7 +126,7 @@ def _scrape_metadata_hydrogen(file, element, charge):
wavelength = float(match.groups()[1]) / 10 # convert Angstroms to nm
upper_level = int(match.groups()[2])
lower_level = int(match.groups()[3])
rate_type_adas = match.groups()[4]
rate_type_adas = match.groups()[4].upper()
if rate_type_adas == 'EXCIT':
rate_type = 'excitation'
elif rate_type_adas == 'RECOM':
Expand All @@ -147,14 +153,13 @@ def _scrape_metadata_hydrogen_like(file, element, charge):
file.seek(0)
lines = file.readlines()

pec_index_header_match = r'^C\s*ISEL\s*WAVELENGTH\s*TRANSITION\s*TYPE'
pec_index_header_match = r'^C\s*ISEL\s*(?:WAVELENGTH|WVLEN\(A\))\s*TRANSITION\s*TYPE'
while not re.match(pec_index_header_match, lines[0], re.IGNORECASE):
lines.pop(0)
index_lines = lines

pec_full_transition_match = r'^[cC]\s*([0-9]*)\.?\s*([0-9]*\.[0-9]*)\s*([0-9]*)[\(\)\.0-9\s]*-\s*([0-9]*)[\(\)\.0-9\s]*([A-Z]*)'
for i in range(len(index_lines)):

pec_full_transition_match = r'^C\s*([0-9]*)\.\s*([0-9]*\.[0-9]*)\s*([0-9]*)[\(\)\.0-9\s]*-\s*([0-9]*)[\(\)\.0-9\s]*([A-Z]*)'
match = re.match(pec_full_transition_match, index_lines[i], re.IGNORECASE)
if not match:
continue
Expand All @@ -163,7 +168,7 @@ def _scrape_metadata_hydrogen_like(file, element, charge):
wavelength = float(match.groups()[1]) / 10 # convert Angstroms to nm
upper_level = int(match.groups()[2])
lower_level = int(match.groups()[3])
rate_type_adas = match.groups()[4]
rate_type_adas = match.groups()[4].upper()
if rate_type_adas == 'EXCIT':
rate_type = 'excitation'
elif rate_type_adas == 'RECOM':
Expand Down Expand Up @@ -193,18 +198,23 @@ def _scrape_metadata_full(file, element, charge):
configuration_lines = []
configuration_dict = {}

configuration_header_match = r'^C\s*Configuration\s*\(2S\+1\)L\(w-1/2\)\s*Energy \(cm\*\*-1\)$'
configuration_header_match = r'^C\s*(?:lv\s+)?Configuration\s*\(2S\+1\)L\(w-1/2\)\s*Energy\s*\(cm(?:\*\*|\^)-1\)\s*$'
while not re.match(configuration_header_match, lines[0], re.IGNORECASE):
lines.pop(0)
pec_index_header_match = r'^C\s*ISEL\s*WAVELENGTH\s*TRANSITION\s*TYPE'
pec_index_header_match = r'^C\s*ISEL\s*(?:WAVELENGTH|WVLEN\(A\))\s*TRANSITION\s*TYPE'
while not re.match(pec_index_header_match, lines[0], re.IGNORECASE):
configuration_lines.append(lines[0])
lines.pop(0)
index_lines = lines

configuration_string_match = (
r'^[cC]\s*([0-9]+)\s*'
r'((?:[0-9][SPDFG][0-9](?:\s+[0-9][SPDFG][0-9])*)|(?:[0-9A-Z]+))\s*'
r'\(([0-9]*\.?[0-9]+)\)'
r'\s*([0-9]+)'
r'\(\s*([0-9]*\.?[0-9]+)\)'
)
for i in range(len(configuration_lines)):

configuration_string_match = r"^C\s*([0-9]*)\s*((?:[0-9][SPDFG][0-9]\s)*)\s*\(([0-9]*\.?[0-9]*)\)([0-9]*)\(\s*([0-9]*\.?[0-9]*)\)"
match = re.match(configuration_string_match, configuration_lines[i], re.IGNORECASE)
if not match:
continue
Expand All @@ -218,9 +228,8 @@ def _scrape_metadata_full(file, element, charge):
configuration_dict[config_id] = (electron_configuration + " " + spin_multiplicity +
total_orbital_quantum_number + total_angular_momentum_quantum_number)

pec_full_transition_match = r'^[cC]\s*([0-9]*)\.?\s*([0-9]*\.[0-9]*)\s*([0-9]*)[\(\)\.0-9\s]*-\s*([0-9]*)[\(\)\.0-9\s]*([A-Z]*)'
for i in range(len(index_lines)):

pec_full_transition_match = r'^C\s*([0-9]*)\.?\s*([0-9]*\.[0-9]*)\s*([0-9]*)[\(\)\.0-9\s]*-\s*([0-9]*)[\(\)\.0-9\s]*([A-Z]*)'
match = re.match(pec_full_transition_match, index_lines[i], re.IGNORECASE)
if not match:
continue
Expand All @@ -231,7 +240,7 @@ def _scrape_metadata_full(file, element, charge):
upper_level = configuration_dict[upper_level_id]
lower_level_id = int(match.groups()[3])
lower_level = configuration_dict[lower_level_id]
rate_type_adas = match.groups()[4]
rate_type_adas = match.groups()[4].upper()
if rate_type_adas == 'EXCIT':
rate_type = 'excitation'
elif rate_type_adas == 'RECOM':
Expand Down
Loading