use strict; my $count = 0; my $skip = 0; while() { next if /^\s+/; if ($skip) { $skip=0; next; } $count++ if /^&#/; $count++ if /^&\w/; # print "$count: "; print; if($count == 2) { $count = 0; print "\n"; $skip = 1; } } # print $count, "\n"; __DATA__ " " " quotation mark ' ' ' apostrophe  & & & ampersand < < < less-than > > > greater-than ¡ ¡ ¡ inverted exclamation mark ¢ ¢ ¢ cent £ £ £ pound ¤ ¤ ¤ currency ¥ ¥ ¥ yen ¦ ¦ ¦ broken vertical bar § § § section ¨ ¨ ¨ spacing diaeresis © © © copyright ª ª ª feminine ordinal indicator « « « angle quotation mark (left) ¬ ¬ ¬ negation ­ ­ ­ soft hyphen ® ® ® registered trademark ¯ ¯ ¯ spacing macron ° ° ° degree ± ± ± plus-or-minus  ² ² ² superscript 2 ³ ³ ³ superscript 3 ´ ´ ´ spacing acute µ µ µ micro ¶ ¶ ¶ paragraph · · · middle dot ¸ ¸ ¸ spacing cedilla ¹ ¹ ¹ superscript 1 º º º masculine ordinal indicator » » » angle quotation mark (right) ¼ ¼ ¼ fraction 1/4 ½ ½ ½ fraction 1/2 ¾ ¾ ¾ fraction 3/4 ¿ ¿ ¿ inverted question mark × × × multiplication ÷ ÷ ÷ division ∀ ∀ for all ∂ ∂ ∂ part ∏ ∏ ∏ prod ∑ ∑ ∑ sum − − − minus ∞ ∞ ∞ infinity ∩ ∩ ∩ cap ∫ ∫ ∫ integral ≈ ≈ ≈ almost equal ≠ ≠ ≠ not equal ≡ ≡ ≡ equivalent ≤ ≤ ≤ less or equal ≥ ≥ ≥ greater or equal Α Α Α Alpha Β Β Β Beta Γ Γ Γ Gamma Δ Δ Δ Delta Ε Ε Ε Epsilon Ζ Ζ Ζ Zeta Η Η Η Eta Θ Θ Θ Theta Ι Ι Ι Iota Κ Κ Κ Kappa Λ Λ Λ Lambda Μ Μ Μ Mu Ν Ν Ν Nu Ξ Ξ Ξ Xi Ο Ο Ο Omicron Π Π Π Pi Ρ Ρ Ρ Rho Σ Σ Σ Sigma Τ Τ Τ Tau Υ Υ Υ Upsilon Φ Φ Φ Phi Χ Χ Χ Chi Ψ Ψ Ψ Psi Ω Ω Ω Omega   α α α alpha β β β beta γ γ γ gamma δ δ δ delta ε ε ε epsilon ζ ζ ζ zeta η η η eta θ θ θ theta ι ι ι iota κ κ κ kappa λ λ λ lambda μ μ μ mu ν ν ν nu ξ ξ ξ xi ο ο ο omicron π π π pi ρ ρ ρ rho ς ς ς sigmaf σ σ σ sigma τ τ τ tau υ υ υ upsilon φ φ φ phi χ χ χ chi ψ ψ ψ psi ω ω ω omega Œ Œ Œ capital ligature OE œ œ œ small ligature oe Š Š Š capital S with caron š š š small S with caron Ÿ Ÿ Ÿ capital Y with diaeres ƒ ƒ ƒ f with hook ˆ ˆ ˆ modifier letter circumflex accent ˜ ˜ ˜ small tilde ‌ ‌ ‌ zero width non-joiner ‍ ‍ ‍ zero width joiner ‎ ‎ ‎ left-to-right mark ‏ ‏ ‏ right-to-left mark – – – en dash — — — em dash ‘ ‘ ‘ left single quotation mark ’ ’ ’ right single quotation mark ‚ ‚ ‚ single low-9 quotation mark “ “ “ left double quotation mark ” ” ” right double quotation mark „ „ „ double low-9 quotation mark † † † dagger ‡ ‡ ‡ double dagger • • • bullet … … … horizontal ellipsis ‰ ‰ ‰ per mille  ′ ′ ′ minutes ″ ″ ″ seconds ‹ ‹ ‹ single left angle quotation › › › single right angle quotation ‾ ‾ ‾ overline € € € euro ™ ™ ™ trademark ← ← ← left arrow ↑ ↑ ↑ up arrow → → → right arrow ↓ ↓ ↓ down arrow ↔ ↔ ↔ left right arrow ◊ ◊ ◊ lozenge ♠ ♠ ♠ spade ♣ ♣ ♣ club ♥ ♥ ♥ heart ♦ ♦ ♦ diamond