import textstat, re

t = open('pfl_body.txt').read()

print("=== READABILITY: EDD PFL Claim Process (body copy) ===")
print(f"Words:                      {textstat.lexicon_count(t)}")
print(f"Sentences:                  {textstat.sentence_count(t)}")
print(f"Avg words/sentence:         {textstat.avg_sentence_length(t):.1f}")
print(f"Flesch Reading Ease:        {textstat.flesch_reading_ease(t):.1f}  (higher=easier; 60-70 = plain)")
print(f"Flesch-Kincaid Grade:       {textstat.flesch_kincaid_grade(t):.1f}")
print(f"Gunning Fog:                {textstat.gunning_fog(t):.1f}")
print(f"SMOG Index:                 {textstat.smog_index(t):.1f}")
print(f"Coleman-Liau:               {textstat.coleman_liau_index(t):.1f}")
print(f"Consensus grade:            {textstat.text_standard(t)}")

# Form / document codes the user must track
codes = sorted(set(re.findall(r'\b(?:DE|CS|SOC|AD)[\s-]?\d{3,4}[A-Z]{0,3}(?:/S)?\b', t)))
print(f"\n=== JARGON LOAD ===")
print(f"Distinct form codes on one page: {len(codes)}")
print("  " + ", ".join(codes))

terms = ["base period","wage replacement","care recipient","qualifying event",
         "covered active duty","physician/practitioner","valid claim","certification",
         "eligibility","determination","CASDI","Statement of Claimant"]
print("\nUndefined domain terms (count of uses):")
for term in terms:
    n = len(re.findall(re.escape(term), t, re.I))
    if n: print(f"  {term:<28} {n}")

# Sentences over 20 words (plain-language ceiling)
sents = [s.strip() for s in re.split(r'(?<=[.!?])\s+', t) if s.strip()]
long_s = [s for s in sents if len(s.split()) > 20]
print(f"\nSentences over 20 words: {len(long_s)} of {len(sents)} ({100*len(long_s)/len(sents):.0f}%)")

# Contrast check
def lum(h):
    h=h.lstrip('#'); r,g,b=[int(h[i:i+2],16)/255 for i in (0,2,4)]
    f=lambda c: c/12.92 if c<=0.03928 else ((c+0.055)/1.055)**2.4
    return 0.2126*f(r)+0.7152*f(g)+0.0722*f(b)
def ratio(a,b):
    l1,l2=sorted([lum(a),lum(b)],reverse=True); return (l1+0.05)/(l2+0.05)

print("\n=== COLOR CONTRAST (WCAG 2.1) ===")
for fg,bg,label in [("#046B46","#FFFFFF","EDD green on white"),
                    ("#FFFFFF","#046B46","white on EDD green"),
                    ("#046B46","#F2F2F2","EDD green on light grey panel")]:
    r=ratio(fg,bg)
    print(f"  {label:<32} {r:>5.2f}:1  AA-normal {'PASS' if r>=4.5 else 'FAIL'} | AA-large {'PASS' if r>=3 else 'FAIL'}")